1 citations · 3 across the 7 of their papers we have counts for
5 papers · 1 filter
Minimally Invasive Steering of Language Models
Taha Entesari, Jingyu Zhang, Daniel Khashabi +1
Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the…
Beyond Average Safety: Chance-Constrained LLM Fine-tuning
Taha Entesari, Mahyar Fazlyab
Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-cri…
Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
Taha Entesari, Mahyar Fazlyab
Reachability analysis of neural networks, which seeks to compute or bound the set of outputs attainable over a given input domain, is central to certifying safety and robustness in…
Compositional Curvature Bounds for Deep Neural Networks
Taha Entesari, Sina Sharifi, Mahyar Fazlyab
A key challenge that threatens the widespread use of neural networks in safety-critical applications is their vulnerability to adversarial attacks. In this paper, we study the seco…
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab, Taha Entesari, Aniket Roy +1
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness prop…