arXiv AI
EvolvAttack: Backdooring self Evolving VLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 24
Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
The paper introduces ShadowMem, a defensive framework that protects large language model agents from long-horizon threats by maintaining a dedicated safety-focused memory. Inspired by the shadow stack concept, ShadowMem stores safety-critical context throughout an agent’s execution and uses this shadow memory to evaluate the risk of upcoming actions before they are carried out. Experiments show that ShadowMem outperforms existing defenses in detection accuracy, detects most attacks early, and adds minimal overhead to agent performance.
arXiv AI
Sep 1
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents
arXiv:2608.30429v1 Announce Type: new Abstract: LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution....
arXiv AI
Jul 29
Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering
arXiv:2607. 25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services.
arXiv AI
Jul 17
Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
arXiv:2607. 14611v1 Announce Type: cross Abstract: A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases.
arXiv AI
Aug 11
Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning
arXiv:2608. 08303v1 Announce Type: new Abstract: Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks.
arXiv Computer Vision
Oct 8
Visual Memory Attacks Can Persist Through The KV Cache
arXiv:2610.09027v1 Announce Type: cross Abstract: Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input con...