🧠 AI Security - ajte0gK4IqIGMcYo8eqW · Scour

Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models

🎯Red Team Academic

Steering Vectors are an Adversarial Attack Surface

🎯Red Team Academic

Towards Evaluating the Robustness of Visual State Space Models

🎯Red Team Academic

AI Will Not Start a Nuclear War, but Humans Might

🎯Red Team News Blog

aifrontiersmedia.substack.com··Substack

When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness

🎯Red Team Academic

PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis

🧮Quantum ML Academic

Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

🐛Fuzzing Academic

Hybrid Adversarial Defence for Natural Language Understanding Tasks

🎯Red Team Academic

SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents

🐛Fuzzing Academic

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents

🎯Red Team Academic

Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models

🎯Red Team Academic

Log in to enable infinite scrolling