Tagged:

2 posts

• Adversarial Examples: The Foundational ML Attack That Still Breaks AI Systems in Production

  Imperceptible perturbations that flip neural network classifications — from FGSM and PGD to physical-world stop-sign attacks and LLM adversarial suffixes. What adversarial examples are, why gradient-based attacks work, how defenses hold up, and what this means for production AI systems today.

  Jul 7, 2026 adversarial-examples evasion-attacks ml-security adversarial-training computer-vision llm-security ai-security

• Adaptive Red Teaming via GRPO: When the Attacker and Defender Train Together

  AdvGRPO introduces a co-training framework where attacker and defender language models evolve together, producing attacks that are both highly effective and transferable — and defenders that outperform safety baselines.

  Jun 13, 2026 red-teaming adversarial-training reinforcement-learning ai-safety attack-defense