Trend Micro’s Top Ten MITRE Evaluation Considerations

The introduction of the MITRE ATT&CK evaluations is a welcomed addition to the third-party testing arena. The ATT&CK framework, and the evaluations in particular, have gone such a long way in helping advance the security industry as a whole, and the individual security products serving the market...

Fooling NLP Systems Through Word Swapping

MIT researchers have built a system that fools natural-language processing systems by swapping words with synonyms: The software, developed by a team at MIT, looks for the words in a sentence that are most important to an NLP classifier and replaces them with a synonym that a human would find...

Monitoring ICS Cyber Operation Tools and Software Exploit Modules To Anticipate Future Threats

There has only been a small number of broadly documented cyber attacks targeting operational technologies OT / industrial control systems ICS over the last decade. While fewer attacks is clearly a good thing, the lack of an adequate sample size to determine risk thresholds can make it difficult f...

Machine learning classifiers trained via gradient descent are vulnerable to arbitrary misclassification attack

Overview Machine learning models trained using gradient descent can be forced to make arbitrary misclassifications by an attacker that can influence the items to be classified. The impact of a misclassification varies widely depending on the ML model's purpose and of what systems it is a part...

Bruce Schneier Proposes 'Hacking Society' for a Better Tomorrow

SAN FRANCISCO – Cybersecurity experts have long stayed in their problem-solving lane when it comes to finding vulnerabilities, patching bugs and keeping networks safe. But maybe it is time they applied their defensive skillsets and adversarial understanding of cyberthreats to help solve some of...

Introduction and Application of Model Hacking

ARCHIVED STORY Introduction and Application of Model Hacking By Steve Povolny · Febraury 19, 2020 Catherine Huang, Ph.D., and Shivangee Trivedi contributed to this blog. The term “Adversarial Machine Learning” AML is a mouthful! The term describes a research field regarding the study and design o...

Introduction and Application of Model Hacking

ARCHIVED STORY Introduction and Application of Model Hacking By Steve Povolny · Febraury 19, 2020 Catherine Huang, Ph.D., and Shivangee Trivedi contributed to this blog. The term “Adversarial Machine Learning” AML is a mouthful! The term describes a research field regarding the study and design o...

Model Hacking ADAS to Pave Safer Roads for Autonomous Vehicles

ARCHIVED STORY Model Hacking ADAS to Pave Safer Roads for Autonomous Vehicles Steve Povolny · FEB 19, 2020 The last several years have been fascinating for those of us who have been eagerly observing the steady move towards autonomous driving. While semi-autonomous vehicles have existed for many...

Mordor - Re-play Adversarial Techniques

The Mordor project provides pre-recorded security events generated by simulated adversarial techniques in the form of JavaScript Object Notation JSON files for easy consumption. The pre-recorded data is categorized by platforms, adversary groups, tactics and techniques defined by the Mitre ATT&CK...

Manipulating Machine Learning Systems by Manipulating Training Data

Interesting research: "TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents": Abstract:: Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-ti...

A Deepfake Deep Dive into the Murky World of Digital Imitation

About a year ago, top deepfake artist Hao Li came to a disturbing realization: Deepfakes, i.e. the technique of human-image synthesis based on artificial intelligence AI to create fake content, is rapidly evolving. In fact, Li believes that in as soon as six months, deepfake videos will be...

Blind Spots in AI Just Might Help Protect Your Privacy

Researchers have found a potential silver lining in so-called adversarial examples, using it to shield sensitive data from snoops...

New machine learning model sifts through the good to unearth the bad in evasive malware

We continuously harden machine learning protections against evasion and adversarial attacks. One of the latest innovations in our protection technology is the addition of a class of hardened malware detection machine learning models called monotonic models to Microsoft Defender ATP's Antivirus...

Addressing the Cyber Security Skills Gap, Part 1

Operating in an adversarial driven world, cyber defenders are faced with many obstacles. In effort to keep pace with our adversarial counterpart, the cyber security skills gap has become the silent oppressor. In Part 1 of this multi-part blog series we will define the implications presented by th...

Fooling Automated Surveillance Cameras with Patchwork Color Printout

Nice bit of adversarial machine learning. The image from this news article is most of what you need to know, but here's the research paper...

Adversarial Machine Learning against Tesla's Autopilot

Researchers have been able to fool Tesla's autopilot in a variety of ways, including convincing it to drive into oncoming traffic. It requires the placement of stickers on the road. Abstract: Keen Security Lab has maintained the security research work on Tesla vehicle and shared our research...

Breaking the Bank: Weakness in Financial AI Applications

Currently, threat actors possess limited access to the technology required to conduct disruptive operations against financial artificial intelligence AI systems and the risk of this targeting type remains low. However, there is a high risk of threat actors leveraging AI as part of disinformation...

RSAC 2019: The Dark Side of Machine Learning

SAN FRANCISCO – The same machine-learning algorithms that made self-driving cars and voice assistants possible can be hacked to turn a cat into guacamole or Bach symphonies into audio-based attacks against a smartphone. These are examples of “adversarial attacks” against machine learning systems...

Cybersecurity for the Public Interest

The Crypto Wars have been waging off-and-on for a quarter-century. On one side is law enforcement, which wants to be able to break encryption, to access devices and communications of terrorists and criminals. On the other are almost every cryptographer and computer security expert, repeatedly...

SANS THIR Summit Wrap Up – “We Have 15 Minutes”

Heading back to San Diego before I get on another flight 30 hours later. Lots of people say "what are you crazy? Why do that?"…to which I say: "we cannot achieve any mission without sacrifice." Going to events like the SANS Threat Hunting IR summit remind just how many dedicated people we have on...