2405.01741

arxiv.org · 4,893 words · saved by 1 readers

N/A

PVF: Understanding AI Vulnerability Against SDCs Xun Jiao, Fred Lin, Harish Dixit, Joel Coburn, Sajin Nair, Abhinav Pandey Han Wang, Venkat Ramesh, Jianyu Huang, Daniel Moore, Sriram Sankar Meta Platforms, Inc Abstract—Reliability of AI systems is a fundamental con- In particular, hardware faults that are not reported…

saved by

Wei Chun Tan

related reading

Evaluating and Enhancing Robustness of Deep Recommendation Systems Against Hardware Errorsarxiv.org
Detecting silent data corruptions in the wildarxiv.org
[2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
[2602.04899] Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoningarxiv.org
[2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
2409.02908arxiv.org
2312.06942arxiv.org
[2606.04071] Covert Influence Between Language Modelsarxiv.org
2310.01405arxiv.org
2310.01405.pdfarxiv.org
2410.21680arxiv.org
AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org