AI security
Open Framework Detects Attack Patterns in Multi-Agent AI Systems
New research introduces an open framework for training security models that detect temporal attack patterns in multi-agent AI workflows through trace-based analysis.
AI security
AI security
Adversarial Attacks on LLM Resume Screeners Reveal AI Security Ga
New research exposes how adversarial techniques can manipulate LLM-based resume screening systems, revealing fundamental security vulnerabilities in specialized AI applications.
AI security
ArcGen: Cross-Architecture Backdoor Detection for Neural Networks
New research introduces ArcGen, a framework that generalizes neural backdoor detection across diverse model architectures without retraining, addressing critical AI security vulnerabilities.
deepfake detection
FaceOff Technologies Launches AI Deepfake Detection Engine
FaceOff Technologies unveils new AI-powered detection platform targeting deepfakes and synthetic fraud, aiming to strengthen digital trust infrastructure for enterprises.
AI security
API Access Enables AI Model Cloning and Safety Bypass
New research reveals how anyone with API access can clone AI models and strip away safety guardrails, creating unregulated copies capable of generating harmful content.
AI security
Browser Extensions Harvesting AI Chats From 8M Users
Security researchers discover browser extensions with 8 million users secretly collecting extended conversations from ChatGPT, Gemini, and other AI platforms, raising major privacy concerns.
AI security
AI Security Battles: Is Robust Alignment an Endless Struggle?
New research examines whether AI security and alignment efforts face fundamental limitations, analyzing the cycle of safety measures and adversarial bypasses in modern AI systems.
AI security
Data Poisoning Attacks: A Technical Guide for AI Engineers
Data poisoning threatens AI model integrity by corrupting training data. Learn attack vectors, detection methods, and defense strategies for protecting ML systems.
AI security
IBM's Adversarial Robustness Toolbox: Stress-Testing AI Security
IBM's open-source ART framework lets developers systematically attack their own AI models to find vulnerabilities before bad actors do. Here's why robustness testing matters.
AI security
Multi-Agent LLMs Team Up to Break AI Safety Guardrails
New research demonstrates how multiple LLMs working together can generate adaptive adversarial attacks that bypass AI safety filters. The technique uses collaborative reasoning to craft prompts that exploit model vulnerabilities more effectively than single-agent approaches.
AI security
Synthetic Data Optimizes Adversarial Attacks on AI Agents
New research demonstrates how synthetic data generation can systematically optimize adversarial attacks against AI agents, revealing critical security vulnerabilities in autonomous systems through automated testing frameworks.
voice cloning
AI Voice Cloning Now Works From Photos Alone
Researchers demonstrate AI can clone voices using just photographs, eliminating the need for audio samples. This breakthrough raises new concerns for synthetic media and digital authenticity verification.