wovepaper — the arXiv observatory

papers

Publications (10)

Reverse Engineering $ℓ_{p}$ attacks: A block-sparse optimization approach with recovery guarantees

Darshan Thaker, Paris Giampouras, RenÃ© Vidal

A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions

Darshan Thaker, Paris Giampouras, RenÃ© Vidal

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Buyun Liang, Jinqi Luo, Liangzu Peng +6

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

Buyun Liang, Liangzu Peng, Jinqi Luo +3

Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations

Iddo Drori, Darshan Thaker, Arjun Srivatsa +15

Scale-Cascaded Diffusion Models for Super-Resolution in Medical Imaging

Darshan Thaker, Mahmoud Mostapha, Radu Miron +2

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

Buyun Liang, Kwan Ho Ryan Chan, Darshan Thaker +2

Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning

Qiang Ma, Suwen Ge, Danyang He +2

Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration

Darshan Thaker, Abhishek Goyal, RenÃ© Vidal

PaCE: Parsimonious Concept Engineering for Large Language Models

Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan +4