Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Sarah Erfani

Sarah Erfani

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2ML×1AI×1Vision×1Robotics×1

Frequent co-authors

Hugo Lyons Keenan1×
Christopher Leckie1×
Xiao Li1×
Xiang Zheng1×
Yifeng Gao1×
Xinyu Xia1×

Research Timeline

2026
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.

Mechanistic Anomaly Detection via Functional Attribution

The paper proposes reframing mechanistic anomaly detection (MAD) as a functional attribution problem, using influence functions to measure how much a model's output depends on specific input samples, achieving state-of-the-art results across various anomaly types and modalities.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRRecentApr 21, 2026

Mechanistic Anomaly Detection via Functional Attribution

Hugo Lyons Keenan, Christopher Leckie, Sarah Erfani

The paper proposes reframing mechanistic anomaly detection (MAD) as a functional attribution problem, using influence functions to measure how much a model's output depends on specific input samples,…

View →
cs.CRcs.AIcs.CVRecentMar 28, 2026

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia +34 more

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

View →