Florian Tramr
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1AI×1
Frequent co-authors
Research Timeline
2026
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper introduces Trojan Hippo, a persistent memory attack that exfiltrates sensitive data from LLM agents by planting dormant payloads into long-term memory, and develops a comprehensive framework to evaluate defenses against it.
Laundering AI Authority with Adversarial Examples
The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI authority laundering.'
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.LGRecentMay 5, 2026
Laundering AI Authority with Adversarial Examples
The paper demonstrates that adversarial examples can be used to manipulate Vision-Language Models (VLMs) into confidently providing authoritative but incorrect information, a process termed 'AI author…
View →
cs.CRcs.AIRecentMay 3, 2026