The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across divers…

The paper introduces DeCNIP, a method for identifying and neutralizing backdoors in large language models using representational analysis and neuron isolation pruning.

This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…

STEP introduces a novel, black-box, retraining-free detector that profiles audio samples using dual perturbation branches to detect backdoor attacks by exploiting the characteristic instability of hid…

The paper introduces Checkerboard, a novel, learning-free clean-label backdoor attack that efficiently poisons training data to compromise model integrity with minimal poisoning budget.

This paper proposes a method to decrease Word Error Rate (WER) and increase recall in Automatic Speech Recognition systems using a certification-inspired mechanism, a Two-Sided Atomic Audit, and a Ran…

The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.

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 introduces Hidden Ads, a novel backdoor attack for Vision-Language Models (VLMs) that injects unauthorized advertisements by exploiting natural, recommendation-seeking user behaviors, mainta…

The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models c…

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.

This paper proposes a physical backdoor attack against deep learning modulation classifiers, utilizing power amplifier non-linear distortions as physical triggers to achieve high attack success rates.

This paper proposes a density-aware attack that constructs triggers by placing poisoned samples in low-density regions of the clean data distribution, achieving high attack success rates even after st…

This paper introduces a novel backdoor attack (ACB) against Reinforcement Learning with Verifiable Rewards (RLVR), demonstrating that poisoning the training data can implant a backdoor that significan…

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.

The paper proposes a novel cross-modal backdoor attack that exploits the vulnerability of lightweight connectors in multimodal LLMs, demonstrating high attack success rates across different modalities…

The paper introduces FlipGuard, a proactive defense framework against Quantization-Conditioned Backdoor (QCB) attacks in Large Language Models (LLMs), achieving high security with negligible performan…