How We Keep 1M Students Safe Daily


We introduced Auditor after learning from our schools that students were using Gmail to express negative emotions such as bullying and self-harm. We made it free so that no school would have to make compromises when it comes to student safety.

Today, Auditor is thriving – scanning 3.5 million emails per day for 1 million students across the world.

‘Within six months of its launch Auditor has scanned more than 100 million emails and saved so many lives – That’s the power of AI and best part is that it’s all free! This is something that each every school should have as kids lives are at stake.’

‘Securly has been having its filtering product around for quite sometime but our core mission has always been ubiquitous safety for kids. Auditor is one such product that is so core to our mission, we decided to give it for free. Since its launch six months ago it has helped save countless number of lives.’ – Neeraj Thakar, VP India R&D Operations

Auditor also ensures that schools are CIPA (Children’s Internet Protection Act) compliant. CIPA requires schools to maintain “the safety and security of minors when using electronic mail, chat rooms, and other forms of direct electronic communications”. However, traditional web-filters do not address this. Many schools reported using Google’s default compliance options to flag emails that contain a predefined set of keywords.

This method is undependable as:

  1. It is prone to lots of False Positives (False Alarms) and False Negatives (Missed Alerts).
  2. Does not scale well in a large District where IT becomes the bottleneck in sorting through these flagged messages.

Instead, Auditor uses an automated sentiment inference approach. For example, consider a post that was flagged by our algorithm:

“slowly im realizing i don’t really have a purpose here say good bye cause Fryday it’s all over <3”

Though the allusion to suicide is clear, it does not contain the keywords usually associated with this kind of behavior. A keyword based approach would not have worked in detecting this.

Freedom of Speech = Freedom to Bully?

cyberbullying, speech, freedom, court, law

In 2014, Michele Carter told Conrad Roy to reenter a carbon-monoxide-filled car and proceed with his suicide attempt. She was charged with involuntary manslaughter as text messages surfaced, ones sent by her encouraging Roy to end his own life.

Her defense claimed that the texts were a form of free speech, protected by the First Amendment: “…verbal conduct can never overcome a person’s willpower to live, and therefore cannot be the cause of suicide…”

The court ruled against her favor, yet a broader debate surrounding Freedom of Speech and its implications for state cyberbullying laws remains unresolved. In compliance with the Child Internet Protection Act, various states have proposed making cyberbullying a criminal offense in order to prevent cyberbullying in school. However, some argue that this infringes upon a student’s First Amendment right, especially if the bullying occurs off-campus during non-school hours.

This past June, the North Carolina Supreme Court repealed its 2009-enacted cyberbullying law after reopening the case of a formerly convicted high school student. The court decided that the law –one prohibiting the use of computers to post (or maliciously encourage others to post) compromising information online– was too broad and violated the Freedom of Speech. Courts are now using a “disruption test” to assess the magnitude of cyberbullying accusations, measuring the extent that a student’s actions impacted the school environment.

“Congress shall make no law respecting an establishment of religion, or prohibiting the free exercise thereof; or abridging the freedom of speech, or of the press; or the right of the people peaceably to assemble, and to petition the government for a redress of grievances.”

Essentially, lawmakers are struggling to identify 1) when “free speech” becomes a threat to someone else’s life and 2) at what point can lawful action be taken. Texas Senator José Menéndez proposed new legislation called “David’s Law”, named after a victim of cyberbullying who later committed suicide. Menéndez claims cyberbullying is distinct from free speech and therefore should be criminalized, citing, “The Supreme Court has ruled our right to free speech is regulated by boundaries. You can’t yell ‘fire’ in a crowded theater… can’t make threats against someone’s life and defend it as free speech.”

17 states have criminalized cyberbullying as part of their cyberbullying prevention initiatives. In the meantime, national organizations are working ceaselessly to reduce the frequency of cyberbullying by educating students about proper online behavior. 

The freedom of speech does not justify bullying. Find out more about the movement against cyberbullying here.

To learn more about cyberbullying, sign up for our parent newsletter below.

The 4 Main Types of Cyberbullying Across the Country

bully, coast, cyberbully, law, online

16% of kids have cyberbullied their peer(s), reports a recent Cyberbullying Research Center study. More often than not, these bullies are motivated by their own anger and frustration. Technology provides refuge and anonymity for such behavior, empowering kids to do and say things they would otherwise not do in person.

From our analysis of 500K social media posts, we found that the majority of aggressive online posts could be broken into the four main categories listed below in order from most frequent to least frequent:

1. Namecalling/Harassment

  • “you’re a f***ing rat close yo mouth and your legs no disrespect tho.”
  • “yea you should hate yourself. as you f***ing should stupid hoe.”

2. Relationship Drama

  • “funny af how you talk s**t about my best friend right in front of me making it seem like yall wanna talk to me… there’s no need for yall to be talking s**t behind her back.  claiming that you ain’t fake and s**t.. bitch f***ing please. you f***ing snake.”
  • “@—— you can go f**k yourself and leave @—— alone…you obviously are jealous. she’s much nicer and better than your lying fake a**.”
  • “@—— stupid mother f***ing dumb a** b***h why don’t you just go have sex with some girls since you’re “famous”

3. Body Image/Looks

  • “if you’re a whore or look like one and you end up showing your slutty-ness and it winds up on my timeline…i will call you a whore and then unfriend you. with no regrets”
  • “she looks like a f***ing jew to me”

4. Threats

  • “fools gonna get beat today. i tried to warn people about lying, they just don’t want to believe me. ha. don’t f**k around with me…”

We also found that certain characteristics differ geographically across the US: students on the East Coast seem to be far more aggressive and confrontational on social media. Namecalling/Harassment posts occur about 14% more on the East Coast than on the West Coast.

Although the reason for this is unclear, it may be due to the lack of a national cyberbullying law. No federal law directly addresses bullying; legislation was introduced in 2009, but no action has been taken since. However, the Children’s Internet Protection Act (2000) requires schools to 1) monitor their students’ online behavior and 2) outline a plan to educate students on proper online behavior. Thus, each state has created their own laws and preventative measures to discourage bullying and online harassment.

Cyberbullying Laws Across the Country

The majority of West Coast states include cyberbullying in their bullying laws, while many East Coast and Midwest states do not. Georgia, Kentucky, and Nebraska have proposed including cyberbullying measures in their current policies.

State bullying laws, updated January 2016

Includes “cyberbullying” Does not include “cyberbullying”














New Hampshire

New Mexico

New York

North Carolina


Rhode Island
















New Jersey

North Dakota




South Carolina

South Dakota



West Virginia



For more information on cyberbullying laws across the country, the Cyberbullying Research Center released a brief review which compares bullying laws by state.  A more comprehensive explanation of each state’s policy can be found on

To learn more about cyberbullying, sign up for our parent newsletter below.

A Cry for Help: in 140 Characters or Less

 “If I die tonight, would anyone cry?”  Amber Cornwell published this post soon before completing suicide in December of 2014.

Social media is the modern-day soliloquy; kids are now more likely to lament emotional distress or seek help via online platforms. Through Machine Learning techniques, we found that Twitter was the overwhelming favorite for kids to vent emotions: 71% of flagged activity* are tweets. However, it is through these same platforms that cyberbullying occurs.

30% of flagged posts* are direct forms of cyberbullying. Interestingly, ⅓ of all students have experienced some type of online harassment.  Teens exposed to cyberbullying are 2.4 times more likely to entertain suicidal notions. Certainty of this causal relationship is demonstrated by terms like “cyberbullicide”, as used in an American Public Health Association study.

Social media interactions can provide a look into a teen’s life, yet red flags are largely ignored due to the casual nature of online culture. Mean comments and threats are posted online all the time; this problem has proliferated into a cyberbullying epidemic, one that large social media platforms are struggling to mitigate. Dick Costolo, CEO of Twitter, admitted, “We suck at dealing with abuse and trolls on the platform and we’ve sucked at it for years.”



Common Sense Media’s “5 Ways to Stop Cyberbullies”. Although this is a great guide for handling cyberbullying, there is a larger issue that still needs to be solved.


Amber was a victim of cyberbullying. So was Thomas Mullaney, and many others who decided to take their own life as a result. To reduce teen suicide and depression, we must eliminate a major root cause: bullying.

This month is National Bullying Prevention Month, a movement to stop bullying and cyberbullying once and for all. To learn more about how to get involved in with your local community’s bullying prevention initiatives, click here.

*Of 500,000 social media posts, 1 in 50 posts were flagged for suspicious behavior related to drugs, profanity, cyberbullying, threats, depression, or suicide.


For more information on cyberbullying prevention, sign up below:

October is National Bullying Prevention Month

This year marks the 10th anniversary of National Bullying Prevention Month. Since 2006, the PACER National Bullying Prevention Center has launched nationwide campaigns to combat bullying during the month of October. In 2010, they introduced plans for cyberbullying prevention. Through community building events and education initiatives, they work to eliminate the notion that bullying is a “rite of passage” that makes kids tougher – as it actually results in devastating consequences such as decreased self-esteem, anxiety, depression, and suicide.

In the past, PACER has partnered with companies like Disney and TLC to build upon their national campaign and amplify its message across multiple platforms to different age groups.

“You are Braver, Stronger and Smarter Than You Think” was a public service announcement produced for National Bullying Prevention Month by Disney in 2015.

How to Get Involved

PACER and community partners host events across the country throughout the month of October. “Run, Walk, Roll, Against Bullying” takes place in 12 different cities, and the symbolic “Unity Day” will be held on Wednesday, October 19.

They also provide online resources, including Classroom and Community Toolkits. Teachers and parents are encouraged to utilize these materials to promote conscientious behavior among their students and foster a supportive environment.

Multiple organizations work in tandem to eradicate bullying and its consequences. Stomp Out Bullying, the national anti-bullying and cyberbullying prevention organization, created Blue Shirt Day: World Day of Bullying Prevention which asks communities to stand in solidarity for anti-bullying by wearing blue clothing on the first Monday of each October.

To find out more information on bullying prevention and how you can join the movement, check out the following resources:


Cyberbullying Prevention for the Classroom

cyberbullying, online student safety, child safety

Online harassment continues to increase each year.

As cyberbullying rates reach an all time high among young adults, what are parents and teachers to do?

Yes, Anti-Bullying Laws do exist and cyberbullying is ILLEGAL!  Laws vary by state, but cover the necessities.  According to the Cyberbullying Research Center, while only 23 states directly mention “cyberbullying”, 48 states include protection against electronic harassment.  These laws essentially grant school systems authority to enact mandatory cyberbullying prevention policies and decide upon appropriate consequences. believes there are 11 key components (shared by each state’s anti-bullying laws) to consider when creating an anti-cyberbullying strategy.

Though seemingly verbose, these components are quite simple and perfectly adaptable to everyday classroom culture.  See below for the *top items to share with your students:

Purpose Statement: Why do we need cyberbullying laws?

1 in 10 students grades 6-12 experienced cyberbullying and 15% of high school students were bullied last year.

Explain to your students why these laws are necessary, and the effects of cyberbullying.  Students who are cyberbullied are more likely to struggle personally and in school.  Bullying can worsen feelings of rejection, isolation, depression, etc. which can lead to suicidal behavior.

Statement of Scope: How far do cyberbullying laws reach, and should they?

Most cyberbullying occurs away from school grounds.

Explain to students that no matter the location, cyberbullying is still criminal and under the jurisdiction of school policy.

Over 25% of states have specified that schools are able to discipline students for incidents that endanger the learning environment off campus.  Federal law allows them to do so; a variety of Supreme Court cases rule in favor of school authority.

Specification of Prohibited Conduct: What actions count as cyberbullying?  

Clearly define and provide examples of what qualifies as cyberbullying.

It seems that many students are unsure about the concept, even casually writing off teasing and taunting online as the norm.  Sending a mean or threatening text, posting hurtful words/images, and impersonating someone online are all considered cyberbullying to a certain extent.  For a more extensive list, see here.

Enumeration of Specific Characteristics: What topics should one avoid?

Harassment need not be based on a specific characteristic to be considered bullying.  Mockery of differentiating factors –race, ethnicity, color, gender, sexual orientation– should not be tolerated.

North Carolina: N.C. Gen. Stat. § 115C-407.15(a) (2010): “Bullying or harassing behavior includes, but is not limited to, acts reasonably perceived as being motivated by any actual or perceived differentiating characteristic, such as race, color, religion, ancestry, national origin, gender, socioeconomic status, academic status, gender identity, physical appearance, sexual orientation, or mental, physical, developmental, or sensory disability, or by association with a person who has or is perceived to have one or more of these characteristics.”

Communication Plan: How can students report cyberbullying?  What are the consequences? How will parents, faculty, and students be involved?

Alert students and parents of the cyberbullying policy and how to get help.

Students should feel safe reporting instances of cyberbullying, and schools should provide avenues of seeking help – hotlines, guidance counselors, etc.  The student body, as well as their parents, should be notified of the cyberbullying policy and consequences of violation.

Take for example a San Ramon Middle School’s policy.  Their “communication plan” lists examples of cyberbullying, consequences (from a minimum of suspension to a maximum of expulsion), and the appropriate supporting education codes.

Training and Preventative Education: What can I do prevent cyberbullying?

The more you know about cyberbullying and how to handle it, the easier it will be to implement prevention methods!  Schools must equip their staff with the tools to stop the bullying at the source! provides training modules for community leaders, teachers, bus drivers, etc. Technology-based solutions are also available for schools to utilize

In addition, teach students to be good digital citizens and respectfully utilize online resources.
*Missing components from Stopbullying’s analysis include Development and Implementation of LEA Policies, Components of LEA Policy, Review of Local Policies, Transparency and Monitoring, Statement of Rights to Other Legal Resources

Much is to be considered when creating overarching anti-cyberbulling measures, and schools try their best.  However, keeping your kids safe from cyberbullying starts at home.  Implementing social media safety measures and monitoring your child’s online activity are just some of the many ways to do so.  For other good resources on cyberbullying prevention check out the National Society for the Prevention of Cruelty to Children.

To learn more about cyberbullying prevention/detection, and other parental controls, sign up for our parent newsletter below.

How to Protect Kids from Cyberbullying

how to stop cyberbullying and how to protect kids from cyberbullying

Search volume of the term “cyberbullying”, which shows a clear upward trend in recent years.
Source: Google Trends.

Teens are already notorious for taunting their peers, and now technology has provided another avenue for adolescents to become involved in destructive behavior. Thus began the rise of cyberbullying: bullying via electronic communication usually occurring in the form of mean-spirited and particularly harmful messages.

The fact that 88% of young adults use cell phones regularly only serves to exacerbate the issue of cyberbullying. In fact, about 43% of kids have reported being bullied online while 87% have witnessed cyberbullying of others. Websites like Facebook, Twitter, and Instagram are hot spots for bullying, as 58% of kids say they have been negatively addressed on social media. However, growing awareness of the topic has led to various initiatives to stop cyberbullying  at home and in school.

Here are a few tips to protect kids from cyberbullying:

Educate kids about cyberbullying

Research indicates that most kids are not completely sure what constitutes the act of cyberbullying. In a recent study about student screen time conducted by Securly, K-12 students spoke very casually about online teasing/taunting as if it were an expected norm.  Many students may not realize when they have gone too far, or when someone else has crossed the line.

Acts that can be considered cyberbullying include using offensive language (e.g., hateful, derogatory, racist, or homophobic remarks), harassment, gossip, or even impersonating someone on the web.  It is important that kids are informed of the cyberbullying resources and support systems available to them  – unfortunately, only 1 in 10 victims reach out to an adult about the abuse.  

Teach students how to be good digital citizens! Qualities of digital citizenship include responsible and considerate behavior on the web. Schools should (and many do) instill a firm anti-cyberbullying policy and a report system in order to prevent cyberbullying.

It’s important for cyberbullying victims to realize they are not alone; too often, kids who are bullied can slip into depression and are as much as 9 times more likely to consider suicide.  And as we have seen in many recent tragic school shootings in the United States, seeking revenge for being bullied or cyberbullied by peers is often the strongest motivation for committing such a violent act. Understanding the ramifications of cyberbullying will help kids be more considerate of how they treat others.

Customize privacy settings on social media

Cyberbullies can be peers, but also strangers on the Internet under anonymous usernames that post hurtful comments.  This can be just as impactful as mean-spirited words from someone they know.  

Kids can limit their social media circles to a positive environment consisting of friends, family, and trusted acquaintances.  This can be as simple as being discriminating when accepting friend requests.  

Most social media sites have features that allow the user to limit who can see their profile. Facebook in particular has a feature that allows users to hide photos from specific people of the user’s choosing.  Check out this article for instructions on how to customize privacy settings on various social media platforms.  

Use anti-cyberbullying technology

Protect kids from cyberbullying by stopping it at the source!  Get kids to think about what they’re about to post by using helpful new technological innovations.

High schooler Trisha Prabhu created an app called “ReThink” which asks kids to think twice about the content which they are posting if the message seems to have a negative tinge. She found that 93% of the time, children chose not to post an offensive message.  The part of the adolescent brain that controls decision making is not fully developed, which explains why young adults often times make rash decisions without fully considering the consequences.

There are also a variety of cyberbullying prevention apps that detect keywords relating to bullying, sexual content, profanity, etc which can help parents monitor their child’s behavior. The recent advances made in machine learning and natural language processing allow some apps to detect sentiments of bullying and self-harm (even in the absence of keywords) used on social media.

To learn more about cyberbullying prevention/detection, and other parental controls, sign up for our parent newsletter below.

Bullying and Self-Harm Detection

Sample Flagged Posts

A big reason school IT Admins are drawn to Securly is our industry-first “Bullying and Self-Harm Detection”. This technology promises to keep students safe on social media by analyzing their posts and alerting school officials of incidents such as cyber-bullying, self-harm, and grief. In theory it sounds quite powerful, but how does our technology work, and more importantly, just how accurate is it?

We’ve come a long way since our successfully funded Kickstarter Project, in which we raised over $50,000 to aid in the research and development to perfect our technology. What makes our offering different from competing solutions can be summed up in a simple phrase: “sentiment analysis”. This means exactly what you are probably thinking. Instead of flagging on certain keywords in isolation, which tends to produce a high rate of false positives, our algorithms interpret the underlying emotion or sentiment behind the post and at that point decide whether or not it warrants being flagged. You can also read our original blog post to get a better understanding of the technical details.

Now on to the million dollar question – does it really work? If you were to ask us this same question a few months ago, we would have said yes, but with a small caveat – training our engine to become more sophisticated and reduce false positives is something that takes a substantial amount of time and effort. We’ve been fortunate enough to have two Securly team members working full-time on feeding our machine tens of thousands of social posts and rooting out false positives.

To best illustrate how far we’ve come, we’ll look at a before-and-after comparison. Below are some posts that we would have flagged in the early days of our technology. Notice that despite the excessive foul language, most of these posts are fairly harmless in their intent.

  • “you the f***ing best”
  • “eenie meenie miney mo you are nothing but a dirty h**. you think youre cute”
  • “this s*** is stupid”
  • “f*** you.”
  • “i hate you so much”
  • “sn sucks d****”
  • “you f***ing hurt me
  • “got 99 problems and a b**** aint one”
  • “b**** keeps staring… better knock her shit off…”
  • “i think you should shut the f**** up !”
  • “@username pero theyre f***ing stupid clues”

Now let’s take a look at our flagged posts after the most recent update. You’ll see that the results are quite different now. Most, if not all, of these posts would warrant an alert to the IT Admin to take further action. If you’re looking at  some of these posts and thinking, “wow, there’s no one word in there that would set off a red flag”, then you truly understand and appreciate the power of what our engineers have developed.


  • “@username @username1 @username2 do y’all just pick on me bc im short? bc i can recall a good 2 times both of yall have tried to beat me up”
  • “@username boy! i will punch you in the throat”
  • “@username b**** i aint tryna say nothing. i didnt get farted on like some people…”
  • “@username stfu [name]”
  • “@username but you da h** im talking about”
  • “@username u so mean to me”
  • “you are a sl**”
  • “go kill yourself”


  • “since i have no friends to get high with.. guess i’m smoking alone tonight :)”
  • “my mom has literally taken every f***ing thing that makes me happy and she wants me to like be hella cool to her. she rude as f***.”
  • “hey guy sorry if i dont talk at all because my friend committed suicide”
  • “have you ever felt like no one wants you in this world :(“
  • “you’re really blessed if you have never had a physical addiction before. not to a person but to a substance. withdrawals will break you.”
  • “do you ever get so heated that you feel like ripping off someones head and yanking their eyes out and stapling them on their knees? orrr..”
  • “i’m ready to f***ing shoot myself”
  • “i sit in the front of the class now and there is so much f***ing porn on my dashboard i hate my life”
  • “my mom over here talking about god is going to punish me for cutting”
  • “depression really sucks especially when you have no support. :(“

Why is this important? With so much reliance on device use in school and at home, students are increasingly turning to social media as an outlet to express themselves. If we think about almost all recent examples of extreme tragedy, the perpetrator has shown signs of troubling behavior, usually presenting itself through social media. And as we can imagine, there are potentially millions of student posts in schools across the globe that need attention but are otherwise going unnoticed. For us, we feel this is the aspect of the product that makes Securly truly secure. We were founded with the mission of protecting kids in all facets of their online life and continuing to improve our Bullying and Self-Harm Detection technology brings us closer to that goal.

Schools using Securly’s services have already noticed the powerful impact this technology can have on students’ well-being. Says Mark Nelson from Romeo Community Schools, “[We’ve] been very impressed with the language sentiment analysis (unavailable from other K-12 service providers); in fact, we used it just last week to inform a parent of an alarming post on Facebook by one of our students. Just one avoidance of a young person harming themselves or others would be worth a thousand times the subscription price.”

Our next roadmap items include: 1) Introducing this feature for users of iPads and our DNS service, and 2) Sending SMS texts to IT admins and parents with high-confidence alerts that warrant intervention. Have other ideas about what would make this offering even better? Please reply to this post and let us know.