2 citations · 6 across the 7 of their papers we have counts for
8 papers
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
Buyun Liang, Jinqi Luo, Liangzu Peng +6
Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability…
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
Buyun Liang, Liangzu Peng, Jinqi Luo +3
Large Language Models (LLMs) are increasingly deployed in high-risk domains. However, state-of-the-art LLMs often exhibit hallucinations, raising serious concerns about their relia…
KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
Buyun Liang, Kwan Ho Ryan Chan, Darshan Thaker +2
Jailbreak attacks exploit specific prompts to bypass LLM safeguards, causing the LLM to generate harmful, inappropriate, and misaligned content. Current jailbreaking methods rely h…
Predicting the Future of the CMS Detector: Crystal Radiation Damage and Machine Learning at the LHC
Bhargav Joshi, Taihui Li, Buyun Liang +2
The 75,848 lead tungstate crystals in CMS experiment at the CERN Large Hadron Collider are used to measure the energy of electrons and photons produced in the proton-proton collisi…
Optimization and Optimizers for Adversarial Robustness
Hengyue Liang, Buyun Liang, Le Peng +3
Empirical robustness evaluation (RE) of deep learning models against adversarial perturbations entails solving nontrivial constrained optimization problems. Existing numerical algo…
NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning
Buyun Liang, Tim Mitchell, Ju Sun
Imposing explicit constraints is relatively new but increasingly pressing in deep learning, stimulated by, e.g., trustworthy AI that performs robust optimization over complicated p…
Optimization for Robustness Evaluation beyond Metrics
Hengyue Liang, Buyun Liang, Ying Cui +2
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems. Popular algorithms for solving these constrai…
NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning
Buyun Liang, Tim Mitchell, Ju Sun
Optimizing nonconvex (NCVX) problems, especially nonsmooth and constrained ones, is an essential part of machine learning. However, it can be hard to reliably solve such problems w…