The paper introduces PoisonForge, a comprehensive benchmark demonstrating that even a small number of targeted poisoned examples can significantly compromise the safety and reliability of instruction-…

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 systematically evaluates static and dynamic adversarial attacks on the ALEX learned index, finding that while static poisoning has minimal impact, dynamic attacks can cause significant slowd…

The paper proposes Cluster Segregation Concealment (CSC), a novel defense that identifies and neutralizes backdoor triggers by relabeling poisoned samples to a virtual class, achieving near-zero attac…

The study demonstrates that poisoned identifier names can survive LLM deobfuscation, even when the model correctly understands the code's semantics, unless the task is reframed from deobfuscation to f…

The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, v…

The paper proposes a universal robustification framework to enhance drift-adaptive malware detectors against combined concept drift and adversarial attacks, significantly reducing attack success rates…

The paper proposes a framework to intentionally evade malware detectors by adding a small number of benign API imports, successfully demonstrating targeted misclassification into a chosen benign categ…

The paper introduces Oracle Poisoning, an attack that corrupts knowledge graphs used by AI agents, demonstrating that all tested models blindly trust poisoned data at high sophistication levels.

This study longitudinally evaluates the adversarial robustness of Android malware detection systems over a decade, finding that temporal separation significantly degrades robustness due to concept dri…

The paper introduces eTAMP, a novel attack that poisons LLM web agents' memory using only environmental observations, demonstrating cross-site and cross-session compromise without direct memory access…

The paper introduces Poison-with-Style (PwS), a stealthy model poisoning attack that exploits developers' inherent code styles as covert triggers to make Code LLMs generate vulnerable code without exp…

The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are in…

The paper identifies a critical vulnerability, the Camouflage Detection Gap (CDG), where standard LLM injection detectors fail dramatically when malicious payloads mimic the target domain's language a…

The paper introduces 'log-substrate prompt injection,' demonstrating that attacker-controlled log fields can be used to manipulate LLM-powered security analysis, with persona hijacking and context man…

The paper introduces GRIEF, a greybox fuzzer that discovers critical, concurrency-related vulnerabilities in LLM serving systems by treating timed multi-request traces as inputs, finding issues like c…

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

RouteGuard is a novel detector that identifies skill poisoning in LLM agents by monitoring structured internal attention shifts, achieving high detection rates on critical skill-injection attacks.

FunPoison introduces a functionality-preserving poisoning technique that injects small, compilable weak-use fragments into code datasets to prevent unauthorized use of CodeLLMs without breaking the co…

This paper addresses the lack of research on adversarial malware generation for Linux ELF binaries by developing a new semantic-preserving generator that achieves a high evasion rate against modern de…