Visual Inception poisons images to hijack long-term memory in agentic recommenders and steer planning, while CognitiveGuard reduces success to about 10% via perceptual sanitization and reasoning verification.
Adbm: Adversarial diffusion bridge model for reliable adversarial purification
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
MEFA enables exact full-gradient white-box attacks on iterative stochastic purification defenses like diffusion and Langevin EBMs by trading recomputation for lower memory, revealing vulnerabilities missed by approximate-gradient methods.
Generative purification with consensus aggregation reduces adversarial illusion attack success rates to near zero on ImageBind while improving alignment on both clean and attacked inputs.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
citing papers explorer
-
Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning
Visual Inception poisons images to hijack long-term memory in agentic recommenders and steer planning, while CognitiveGuard reduces success to about 10% via perceptual sanitization and reasoning verification.
-
Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations
MEFA enables exact full-gradient white-box attacks on iterative stochastic purification defenses like diffusion and Langevin EBMs by trading recomputation for lower memory, revealing vulnerabilities missed by approximate-gradient methods.
-
Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings
Generative purification with consensus aggregation reduces adversarial illusion attack success rates to near zero on ImageBind while improving alignment on both clean and attacked inputs.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.