Inga Strmke
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×2AI×1
Frequent co-authors
Research Timeline
2026
Position: AI Security Policy Should Target Systems, Not Models
The paper demonstrates that advanced capabilities, such as jailbreaking large language models and finding software vulnerabilities, can be achieved effectively at zero cost by coordinating multiple small LLM agents within a system scaffold.
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
The paper demonstrates that cryptographically undetectable backdoors can be embedded into modern, state-of-the-art neural networks by exploiting inherent, latent geometric properties of the learned representation space.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.LGRecentMay 13, 2026
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
The paper demonstrates that cryptographically undetectable backdoors can be embedded into modern, state-of-the-art neural networks by exploiting inherent, latent geometric properties of the learned re…
View →
cs.CRcs.AIcs.LGRecentMay 10, 2026