arXiv AI
Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
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 AI
Jul 24
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv Computation and Language
2d ago
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...
arXiv AI
Jun 2
Perturbation Effects on Accuracy and Fairness among Similar Individuals
arXiv:2404. 01356v3 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
arXiv AI
Jul 1
Perturbation Effects on Robustness and Individual Fairness
arXiv:2404. 01356v4 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
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.