Dana Drachsler-Cohen

activity

20242026

collaborators

3 papers

cs.LG2026

Tight Robustness Certification Through the Convex Hull of $ℓ_{0}$ Attacks

Yuval Shapira, Dana Drachsler-Cohen

Few-pixel attacks mislead a classifier by modifying a few pixels of an image. Their perturbation space is an $ℓ_{0}$ -ball, which is not convex, unlike $ℓ_{p}$ -balls for $p \geq 1$ .…

cs.LG2025

Mini-Batch Robustness Verification of Deep Neural Networks

Saar Tzour-Shaday, Dana Drachsler-Cohen

Neural network image classifiers are ubiquitous in many safety-critical applications. However, they are susceptible to adversarial attacks. To understand their robustness to attack…

cs.LG2024

Boosting Few-Pixel Robustness Verification via Covering Verification Designs

Yuval Shapira, Naor Wiesel, Shahar Shabelman +1

Proving local robustness is crucial to increase the reliability of neural networks. While many verifiers prove robustness in $L_{\infty}$ $I^µ$ -balls, very little work deals with robu…

Tight Robustness Certification Through the Convex Hull of ℓ0​ Attacks

Mini-Batch Robustness Verification of Deep Neural Networks

Boosting Few-Pixel Robustness Verification via Covering Verification Designs

Tight Robustness Certification Through the Convex Hull of $ℓ_{0}$ Attacks