Targeted Bit-Flip Attacks on LLM-Based Agents
Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based agents with multi-stage pipelines and external tools present new attack surfaces, which remain unexplored. This work introduces Flip-Agent, the first targeted BFA framework for LLM-based agents, manipulating both final outputs and tool invocations. Our experiments show that Flip-Agent significantly outperforms existing targeted BFAs on real-world agent tasks, revealing a critical vulnerability in LLM-based agent systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation
Vision Transformers (ViTs) have experienced significant progress and are quantized for deployment in resource-constrained applications. Quantized models are vulnerable to targeted bit-flip attacks (BFAs). A targeted …
Approaching the Harm of Gradient Attacks While Only Flipping Labels
Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, ther…
Data PoisoningTFL: Targeted Bit-Flip Attack on Large Language Model
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-…
Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code Matching
Deep neural networks (DNNs) have been shown to be vulnerable against adversarial weight bit-flip attacks through hardware-induced fault-injection methods on the memory systems where network parameters are stored. Rec…
QuantizationPrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips
We introduce a new class of attacks on commercial-scale (human-aligned) language models that induce jailbreaking through targeted bitwise corruptions in model parameters. Our adversary can jailbreak billion-parameter lan…
Computational Efficiency