Eugene Bagdasarian
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2NLP×1Society×1
Frequent co-authors
Research Timeline
2026
Contrastive Privacy: A Semantic Approach to Measuring Privacy of AI-based Sanitization
The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.
AI Agents May Always Fall for Prompt Injections
The paper argues that prompt injection is a fundamental vulnerability in AI agents, proposing that Contextual Integrity (CI) offers a principled framework to understand and mitigate context-sensitive failures, suggesting that current defenses are insufficient.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CLcs.CYRecentMay 17, 2026
AI Agents May Always Fall for Prompt Injections
The paper argues that prompt injection is a fundamental vulnerability in AI agents, proposing that Contextual Integrity (CI) offers a principled framework to understand and mitigate context-sensitive…
View →
cs.CRRecentMay 3, 2026