25 citations · 25 across the 4 of their papers we have counts for
5 papers
Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs
Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1
Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit harmful or unintended content. Wh…
LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo +1
Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain…
A Review and Comparison of AI Enhanced Side Channel Analysis
Max Panoff, Honggang Yu, Haoqi Shan +1
Side Channel Analysis (SCA) presents a clear threat to privacy and security in modern computing systems. The vast majority of communications are secured through cryptographic algor…
Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers
Honggang Yu, Shihfeng Zeng, Teng Zhang +2
Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled aro…
Active Learning in Gaussian Process State Space Model
Hon Sum Alec Yu, Dingling Yao, Christoph Zimmer +2
We investigate active learning in Gaussian Process state-space models (GPSSM). Our problem is to actively steer the system through latent states by determining its inputs such that…