13 citations · 22 across the 11 of their papers we have counts for
12 papers
ARENA: Automated Red-Teaming for Large Audio Language Models
Jiaming He, Zhicong Huang, Tian Jin +5
Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that…
Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency and Recovery Robustness
Haoting Qian, Qingjie Zhang, Zhicong Huang +2
Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Current unlearning benchmarks inc…
DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models
Zhicong Huang, Cheng Hong, Tao Wei
Cloud-based language model services routinely process prompts containing sensitive information. Obfuscation-based defenses---including ObfusLM, SentinelLMs, TextObfuscator, and DPN…
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Changyue Li, Jiaming He, Youliang Yuan +4
Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety alignment. To recover safety…
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
Zhen Sun, Yifan Liao, Zhicong Huang +4
Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and…
Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
Jialin Wu, Wei Shi, Han Shen +5
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textu…
FIT to Forget: Robust Continual Unlearning for Large Language Models
Xiaoyu Xu, Minxin Du, Kun Fang +5
While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing…
Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
Changyue Li, Jiaying Li, Youliang Yuan +3
Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-A…
Fingerprinting LLMs via Prompt Injection
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li +4
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one mod…
PUMA: Secure Inference of LLaMA-7B in Five Minutes
Ye Dong, Wen-jie Lu, Yancheng Zheng +7
With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts…
Privacy-preserving collaborative machine learning on genomic data using TensorFlow
Cheng Hong, Zhicong Huang, Wen-jie Lu +4
Machine learning (ML) methods have been widely used in genomic studies. However, genomic data are often held by different stakeholders (e.g. hospitals, universities, and healthcare…
Quantification of the Leakage in Federated Learning
Zhaorui Li, Zhicong Huang, Chaochao Chen +1
With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work…