Nils Lukas
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×2Society×2ML×2
Frequent co-authors
Research Timeline
2026
Robust Safety Monitoring of Language Models via Activation Watermarking
This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against such threats.
Watermarking Should Be Treated as a Monitoring Primitive
The paper argues that watermarking must be viewed as a monitoring primitive, introducing an observer-based threat model that shows even zero-bit watermarking can enable entity-level attribution through signal aggregation.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.CYRecentMay 13, 2026
Watermarking Should Be Treated as a Monitoring Primitive
The paper argues that watermarking must be viewed as a monitoring primitive, introducing an observer-based threat model that shows even zero-bit watermarking can enable entity-level attribution throug…
View →
cs.CRcs.AIcs.CYRecentMar 24, 2026