ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Michael Backes

Michael Backes

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

7

papers

52

total citations

papers (7)

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

Captured by Captions: On Memorization and its Mitigation in CLIP Models

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Generating Less Certain Adversarial Examples Improves Robust Generalization

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions

Position: TrustLLM: Trustworthiness in Large Language Models

Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing