#PGD attack
5 related articles
·3 min
Adversarial RL: Why Are Critic Attacks Stronger in Multi-Agent Environments?
The classic Zhang et al. paper says Critic attacks are weaker than Actor attacks, but an experimenter observed the opposite in multi-agent PPO. This article dives into SA-MDP, continuous action spaces, and multi-agent non-stationarity in adversarial RL.
Read more →
·6 min
AI Agent Security in Practice: 7 Attack Techniques and a Five-Layer Defense System
An in-depth breakdown of the 7 major attack techniques against AI agents (prompt injection, data poisoning, image attacks, etc.) and a five-layer defense system, with real cases from Doubao and DeepSeek.
Read more →
Anti-AI Fonts: Adversarial Typography …
·3 min
Anti-AI Fonts: Adversarial Typography That Humans Can Read but Machines Can't
Anti-AI fonts use adversarial glyph design to exploit the perceptual gap between human and machine vision, blocking OCR and LLM scraping. A deep dive into the tech, limits, and data sovereignty implications.
Read more →
·2 min
Anti-Surveillance Fashion: How Adversarial Examples Can Make Cameras Fail to Recognize You
Anti-surveillance fashion uses adversarial examples to fool facial recognition and person Re-ID systems. We break down the tech, real-world limits, and what it means for privacy in a surveillance society.
Read more →
·3 min
AI Safety ≠ Cybersecurity: Gray Swan Founders Detail a New Paradigm for Red-Teaming
OpenAI board member Zico Kolter and Gray Swan CEO Matt Fredrikson explain why AI safety differs fundamentally from cybersecurity and how red-teaming must evolve into a systematic engineering discipline.
Read more →