arXiv AI
The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 25
Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.
arXiv AI
Aug 5
Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.
arXiv AI
Jun 12
SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent Systems
arXiv:2606. 12703v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions.
arXiv AI
Jul 23
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
arXiv:2607. 19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can smuggle instructions.
arXiv AI
Jul 29
Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
arXiv Machine Learning
Jul 30
Adaptively Robust LLM Monitoring via Activation Watermarking
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.