The paper introduces Terminal Wrench, a comprehensive dataset of 331 reward-hackable terminal-agent environments and 3,632 exploit trajectories, demonstrating that detection of reward hacking degrades…

MemMorph introduces a novel memory poisoning attack that biases LLM agent tool selection by injecting crafted records into the agent's long-term memory, achieving high success rates even against moder…

This paper presents SCP, a cache partitioning design that combines strict eviction isolation with write-shared coherence to mitigate eviction-based cache side channels.

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper introduces CanaryRAG, a novel dual-path runtime defense mechanism that detects RAG Knowledge Base Leakage attacks by embedding canary tokens into retrieved knowledge chunks.

The paper demonstrates that structural protection mechanisms are the dominant factor in maintaining high performance for KV cache eviction policies, often surpassing the benefits of complex scoring al…

This paper analyzes the Loki e-voting protocol, demonstrating that while it attempts to solve coercion-resistance without pre-agreed secrets, it remains vulnerable to specific attacks, suggesting that…

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk…

Evo-Attacker introduces a memory-augmented reinforcement learning framework to perform generalized, long-horizon tool attacks on LLM-MAS, significantly outperforming existing methods.

The paper introduces STRIKE, a multi-dimensional structured taxonomy designed to provide a comprehensive and unified framework for classifying the rapidly evolving complexity of modern cybercrimes.

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…

The paper constructs a large, adversarial malware dataset from real-world binaries, demonstrating high evasion rates and showing that even small amounts of poisoned data can severely compromise malwar…

The paper introduces HARP, a new methodology to measure how localized harm (like compromising one agent) can be amplified into significant, system-wide harm within complex multi-agent LLM workflows.

This paper introduces Back-Reveal, an attack demonstrating that backdoored LLM agents can systematically exfiltrate sensitive user data by embedding semantic triggers into tool-use mechanisms.

The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…

The paper introduces DEJA, an automated black-box attack framework that generates stealthy adversarial documents to induce 'soft failures' in RAG systems, degrading utility without triggering overt re…

The paper introduces SLEIGHT-Bench, a benchmark of 40 synthetic attacks, demonstrating that current LLM monitor systems fail to detect a significant number of covert, harmful actions executed by codin…

The paper introduces and measures 'accidental meltdown,' a new type of unsafe agent behavior triggered by benign environmental errors, finding that such meltdowns occur frequently and often involve hi…

HammerSim is a new gem5-based framework that provides full-system visibility to model the RowHammer vulnerability, allowing researchers to study complex OS effects and hardware/software mitigations.