7 papers
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
Yan Scholten, Sophie Xhonneux, Leo Schwinn +1
Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcin…
Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
Aman Saxena, Jan Schuchardt, Yan Scholten +1
Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomiz…
Sampling-aware Adversarial Attacks Against Large Language Models
Tim Beyer, Yan Scholten, Leo Schwinn +1
To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typ…
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
Yan Scholten, Stephan Günnemann
Conformal prediction provides model-agnostic and distribution-free uncertainty quantification through prediction sets that are guaranteed to include the ground truth with any user-…
Assessing Robustness via Score-Based Adversarial Image Generation
Marcel Kollovieh, Lukas Gosch, Marten Lienen +3
Most adversarial attacks and defenses focus on perturbations within small -norm constraints. However, threat models cannot capture all relevant semantics-preservin…
A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
Yan Scholten, Stephan Günnemann, Leo Schwinn
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. Howe…