arXiv Computer Vision
Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 3
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
arXiv:2606. 02947v1 Announce Type: new Abstract: Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks.
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
Sep 30
Selective Channel Restoration for Backdoored Vision-Language Models
arXiv:2609.37759v1 Announce Type: cross Abstract: Vision-language models (VLMs) exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data....
arXiv AI
Aug 26
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
arXiv:2608.24354v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may...
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.
arXiv Machine Learning
Oct 3
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
The paper introduces NEEDLE, a training‑free technique for removing backdoors from large language models. After a trigger is identified, NEEDLE estimates a backdoor direction and a refusal subspace using activation vectors, then applies sequential weight orthogonalisation to suppress the backdoor while preserving refusal‑related representations. The method requires no clean reference model or original poisoned data and achieves the lowest attack success rate and minimal impact on model performance across multiple model families and attack types.