arXiv AI
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 4
Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers
The paper introduces TRIM, a black‑box defense for backdoor attacks in computer vision models. TRIM identifies and removes malicious trigger regions at inference time using region‑based segmentation, adaptive trigger discovery via inpainting and diffusion, and selective purification, without needing model internals, training data, or clean samples. Experiments on various datasets and trigger types show TRIM reduces attack success rates to as low as 1.16% while maintaining high clean accuracy.
arXiv AI
Jul 23
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv Computer Vision
Sep 22
BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
arXiv Computer Vision
Oct 8
Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions
arXiv:2610.09941v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are increasingly deployed in safety-critical applications, yet they remain vulnerable to backdoor attacks. Defendi...
Hugging Face Trending Papers
Jul 22
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
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.