machine learning
Vulnerabilities for AI and ML Applications are Skyrocketing
Nathan Eddy | | AI, BentoML, machine learning, ML Flow, open source, pytorch, Ray, Remote Code Execution, Triton Inference Server
In their haste to deploy LLM tools, organizations may overlook crucial security practices. The rise in threats like Remote Code Execution indicates an urgent need to improve security measures in AI development ...
Security Boulevard
Unveiling The Applications and Distinctions of Machine Learning and Artificial Intelligence in Cybersecurity
Joe Ariganello | | AI, AI Cybersecurity, AI Network monitoring, Artificial Intelligence, Blog, Cybersecurity using AI, machine learning, Self-Supervised AI, Third Wave AI, Uncategorized
The terms "machine learning" and "artificial intelligence" are frequently used in cybersecurity, often interchangeably, leading to confusion about their precise meanings and applications. Both machine learning and artificial intelligence play pivotal roles ...
Relishing new Fickling features for securing ML systems
By Suha S. Hussain We’ve added new features to Fickling to offer enhanced threat detection and analysis across a broad spectrum of machine learning (ML) workflows. Fickling is a decompiler, static analyzer, ...
Our response to the US Army’s RFI on developing AIBOM tools
By Michael Brown and Adelin Travers The US Army’s Program Executive Office for Intelligence, Electronic Warfare and Sensors (PEO IEW&S) recently issued a request for information (RFI) on methods to implement and ...
The Cybersecurity Horizon: AI, Resilience and Collaboration in 2024
Steve Winterfeld | | AI, Cybersecurity, horizon, Insights, machine learning, people, processes, Tech
As we peer into the future, it is imperative to acknowledge the profound impact that artificial intelligence (AI) is having on the cybersecurity arena ...
Security Boulevard
Celebrating our 2023 open-source contributions
Trail of Bits | | blockchain, cryptography, Ecosystem Security, machine learning, open source, osquery, supply chain
At Trail of Bits, we pride ourselves on making our best tools open source, such as Slither, PolyTracker, and RPC Investigator. But while this post is about open source, it’s not about ...
Poisoning AI Models
Bruce Schneier | | academic papers, Artificial Intelligence, LLM, machine learning, threat models, Uncategorized
New research into poisoning AI models: The researchers first trained the AI models using supervised learning and then used additional “safety training” methods, including more supervised learning, reinforcement learning, and adversarial training ...
Protect AI Report Surfaces MLflow Security Vulnerabilities
Michael Vizard | | lifecycle management, LLMs, machine learning, ML, open source, Protect AI, rce, Remote Code Execution
Protect AI identified RCE vulnerabilities in the MLflow life cycle management tool that can be used to compromise AI models ...
Security Boulevard
Our thoughts on AIxCC’s competition format
By Michael Brown Late last month, DARPA officially opened registration for their AI Cyber Challenge (AIxCC). As part of the festivities, DARPA also released some highly anticipated information about the competition: a ...
LeftoverLocals: Listening to LLM responses through leaked GPU local memory
By Tyler Sorensen and Heidy Khlaaf We are disclosing LeftoverLocals: a vulnerability that allows recovery of data from GPU local memory created by another process on Apple, Qualcomm, AMD, and Imagination GPUs ...