Ph.D Students

• Anthony J. Hughes (Univ. of Sheffield), Mitigating PII Leakage using Circuit Patching Fall'25 →ArXiv'25
• Samuel Sousa (TU Graz), SHAPr: Membership Privacy Risk Scores for ML Winter'24
• Jan Aalmoes (INRIA), On the Alignment of Group Fairness with Attribute Privacy 2023 →WISE'24

Master's Students

• Lipeng (Tony) He, Locket: Robust Feature-Locking Technique for Large Language Models 2025-27 →ArXiv'25
• Prach Chantasantitam, Towards Verifiable Properties of Generative Models 2025
• Anudeep Das, Espresso: Robust Concept Filtering in T2I Models 2024 → Best Paper@CODASPY'25
• Asim Waheed, On Using Embeddings for Ownership Verification of GNNs 2021-23 →IEEE S&P'24

Undergraduate Students

• Ayaan Nadamal, Hardware-assisted Attestations for Agents against Prompt Injection Spring'25
• Shihan Sharar, Hardware-assisted Attestations for Agents against Prompt Injection Spring'25
• Lipeng (Tony) He, SoK: Interactions among ML Risks with Colluding Adversaries Winter'25
• Erin Li, Quantifying Training Data Copying in Graph Generative Models Fall'23
• Anudeep Das, Attesting Distributional Properties of ML Training Data Fall'22 → ESORICS'24