arXiv Machine Learning
Backdoor Mitigation in Decentralized LLM Fine-Tuning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
1d ago
Backdoor Containment via Expert Quarantine and Shutdown in LLMs
The paper introduces Quarantined Expert Shutdown (QES), a new backdoor containment strategy for large language models. QES allows backdoor learning to occur during training but routes it into a designated, quarantined expert that can be disabled at deployment. The method achieves significant reductions in attack success rates while largely preserving model utility.
arXiv Machine Learning
Jul 30
ToxScreen: Detecting Whether an LLM Has Been Poisoned
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
Hugging Face Trending Papers
Jul 29
ToxScreen: Detecting Whether an LLM Has Been Poisoned
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv AI
Sep 1
Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection
arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later pri...
arXiv AI
2d ago
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
The paper investigates how inference optimization for large language models can introduce numerical inconsistencies that trigger hidden backdoors. It introduces two types of optimization‑triggered backdoors: the Input‑Specific Optimization Backdoor (ISOB) and the Universal Optimization Backdoor (UOB), the latter enabling a model to remain benign under normal execution but activate a backdoor when optimization is applied. Experiments on seven open‑source LLMs, across multiple tasks and optimization backends, show UOB can achieve up to 100% attack success while maintaining clean accuracy, and the authors propose three defenses that reduce the attack success rate to 0.02.
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.