3 citations · 6 across the 9 of their papers we have counts for
9 papers
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
Xiaoxia Li, Siyuan Liang, Jiyi Zhang +3
Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where craf…
Domain Bridge: Generative model-based domain forensic for black-box models
Jiyi Zhang, Han Fang, Ee-Chien Chang
In forensic investigations of machine learning models, techniques that determine a model's data domain play an essential role, with prior work relying on large-scale corpora like I…
Adaptive Attractors: A Defense Strategy against ML Adversarial Collusion Attacks
Jiyi Zhang, Han Fang, Ee-Chien Chang
In the seller-buyer setting on machine learning models, the seller generates different copies based on the original model and distributes them to different buyers, such that advers…
Finding Meaningful Distributions of ML Black-boxes under Forensic Investigation
Jiyi Zhang, Han Fang, Hwee Kuan Lee +1
Given a poorly documented neural network model, we take the perspective of a forensic investigator who wants to find out the model's data domain (e.g. whether on face images or tra…
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence
Han Fang, Jiyi Zhang, Yupeng Qiu +3
Deep neural networks are vulnerable to adversarial attacks. In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the part…
De-END: Decoder-driven Watermarking Network
Han Fang, Zhaoyang Jia, Yupeng Qiu +3
With recent advances in machine learning, researchers are now able to solve traditional problems with new solutions. In the area of digital watermarking, deep-learning-based waterm…
Mitigating Adversarial Attacks by Distributing Different Copies to Different Users
Jiyi Zhang, Han Fang, Wesley Joon-Wie Tann +3
Machine learning models are vulnerable to adversarial attacks. In this paper, we consider the scenario where a model is distributed to multiple buyers, among which a malicious buye…
Confusing and Detecting ML Adversarial Attacks with Injected Attractors
Jiyi Zhang, Ee-Chien Chang, Hwee Kuan Lee
Many machine learning adversarial attacks find adversarial samples of a victim model by following the gradient of some attack objective functions, either explicitly…
Flipped-Adversarial AutoEncoders
Jiyi Zhang, Hung Dang, Hwee Kuan Lee +1
We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an en…