1.5k citations · 2.4k across the 38 of their papers we have counts for
5 papers · 1 filter
Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias
Shir Bernstein, David Beste, Daniel Ayzenshteyn +2
Large Language Models (LLMs) are increasingly trusted to perform automated code review and static analysis at scale, supporting tasks such as vulnerability detection, summarization…
PEAS: A Strategy for Crafting Transferable Adversarial Examples
Bar Avraham, Yisroel Mirsky
Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substi…
Transpose Attack: Stealing Datasets with Bidirectional Training
Guy Amit, Mosh Levy, Yisroel Mirsky
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on…
Transferability Ranking of Adversarial Examples
Mosh Levy, Guy Amit, Yuval Elovici +1
Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on wh…
Online Budgeted Learning for Classifier Induction
Eran Fainman, Bracha Shapira, Lior Rokach +1
In real-world machine learning applications, there is a cost associated with sampling of different features. Budgeted learning can be used to select which feature-values to acquire…