Zonghao Ying

The account motivates complementary defenses: strengthen resistance and recovery alongside prevention of spontaneous deviations, and audit and restrict unintended communication paths that can turn local failures into collective loss of control.

These results show how a latent loss of control can become an external violation: the task objective remains intact, but an executable opportunity can turn a missing control boundary into consequential action.

Extreme fidelity loss reveals critical vulnerabilities in long-horizon tasks that standard accuracy metrics overlook.

Indirect prompt injection can compromise AI systems like DeepSeek Harness, with attack success rates reaching up to 25.5% under certain conditions.

SkillSentry reveals that dynamic testing can uncover harmful agent behaviors that static analysis fails to detect, achieving unprecedented accuracy in safety evaluations.

SkillJack reveals that self-evolving agents can unknowingly incorporate malicious skills, making traditional safety measures ineffective against persistent threats.

SafeFlow reveals that multi-agent systems can obscure malicious intent through task decomposition, but a semantic information-flow approach can effectively counteract this vulnerability.

SafeGen boosts VLMAD performance by over 24% in safety-critical scenario generation, bridging the sim-to-real gap that has long plagued autonomous driving systems.

MIND redefines adversarial prompt generation, achieving a staggering 95.62% success rate by intelligently interpreting model defenses rather than relying on brute-force tactics.

Adversarial attacks on vision-language agents reveal critical vulnerabilities, with multi-view optimization strategies proving significantly more effective than isolated approaches.

AI-Infra-Guard reveals that a unified security framework can effectively address the diverse attack surfaces of AI agents, making it a game-changer for AI safety.