BYORn defends autoregressive vision-language models against backdoor attacks in supervised fine-tuning by dynamically replacing semantically implausible poisoned responses with model-generated alternatives, improving robustness while preserving clean performance.
Revisiting backdoor attacks against large vision-language models.arXiv preprint arXiv:2406.18844
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
TCAP detects backdoor samples in MLLM fine-tuning via tri-component attention profiling, GMM-based head identification, and EM vote aggregation.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
citing papers explorer
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.