2 citations · 3 across the 9 of their papers we have counts for
9 papers
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
Amit LeVi, Raz Lapid, Rom Himelstein +3
Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…
Silenced Biases: The Dark Side LLMs Learned to Refuse
Rom Himelstein, Amit LeVi, Brit Youngmann +2
Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause sign…
Representing LLMs in Prompt Semantic Task Space
Idan Kashani, Avi Mendelson, Yaniv Nemcovsky
Large language models (LLMs) achieve impressive results over various tasks, and ever-expanding public repositories contain an abundance of pre-trained models. Therefore, identifyin…
Jailbreak Attack Initializations as Extractors of Compliance Directions
Amit Levi, Rom Himelstein, Yaniv Nemcovsky +2
Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initiali…
Sparse patches adversarial attacks via extrapolating point-wise information
Yaniv Nemcovsky, Avi Mendelson, Chaim Baskin
Sparse and patch adversarial attacks were previously shown to be applicable in realistic settings and are considered a security risk to autonomous systems. Sparse adversarial pertu…
Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
Yaniv Nemcovsky, Matan Jacoby, Alex M. Bronstein +1
Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. W…
Colored Noise Injection for Training Adversarially Robust Neural Networks
Evgenii Zheltonozhskii, Chaim Baskin, Yaniv Nemcovsky +3
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that le…
On the generalization of bayesian deep nets for multi-class classification
Yossi Adi, Yaniv Nemcovsky, Alex Schwing +1
Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively. However, to obtain bounds, current techniques use stri…
Smoothed Inference for Adversarially-Trained Models
Yaniv Nemcovsky, Evgenii Zheltonozhskii, Chaim Baskin +4
Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g.,…