The paper proposes DFBScanner, a lightweight static parameter inspection framework that detects backdoor attacks by analyzing anomalous parameter updates in the final classification layer, achieving f…

This paper introduces the first backdoor attack specifically targeting pipeline parallelism in decentralized post-training, demonstrating that a limited adversary controlling an intermediate stage can…

The paper introduces CodeTracer, a forensic framework to trace malicious code completions back to the backdoor fine-tuning data.

The paper proposes HTell, a fast and lightweight data-free backdoor detector that analyzes the abnormal response concentration of backdoored models on the target class using random latent probes appli…

This paper formulates neural backdoor defense as a coreset selection problem and uses Cumulative Entropy as selection criterion to focus on benign samples, constructing a benign coreset for training a…

Patcher is a post-hoc defense framework that repairs backdoored large language models by localizing hidden triggers and patching the model using only a single reported failure case.

This paper surveys the security vulnerabilities of Variational Quantum Circuits (VQCs) to backdoor attacks, detailing various attack mechanisms and analyzing current detection and defense strategies.

The paper introduces a stateful agent backdoor that allows malicious attacks to persist and execute incrementally across multiple sessions, significantly enhancing the threat model for LLM-based agent…

The paper introduces MetaBackdoor, a novel class of LLM backdoor attacks that exploits positional encoding (length-based triggers) rather than requiring modifications to the textual content.

An adversarial model trainer can plant statistically undetectable backdoors in deep neural networks, providing access to adversarial examples.

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific…

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 compares two sparse autoencoder architectures, finding that Differential SAEs (Diff-SAE) significantly outperform Crosscoders in isolating backdoor-related features in language models.

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality…

The paper introduces BadStyle, a novel backdoor attack framework that generates natural, stealthy poisoned samples using LLMs to compromise various LLMs with high success rates and robust activation.

The paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing the backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detectors f…

This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-l…

BackFlush introduces a novel, knowledge-free framework that detects and eliminates unknown backdoor attacks in LLMs while simultaneously preserving existing watermarks, achieving high detection rates…

The paper proposes a novel Text-Guided Backdoor (TGB) attack that uses common words in text descriptions as stealthy triggers for multimodal models, enhancing practicality and controllability.

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.