Giuseppe Ateniese
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2
Frequent co-authors
Research Timeline
2026
TENNOR: Trustworthy Execution for Neural Networks through Obliviousness and Retrievals
TENNOR is a system that enables efficient and private training of wide neural networks in untrusted cloud environments by using doubly oblivious primitives and a novel memory-efficient hashing scheme.
Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
The paper demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output from clean images.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 9, 2026
Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal
The paper demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output fro…
View →
cs.CRRecentMay 8, 2026