1 citations · 1 across the 6 of their papers we have counts for
7 papers
From Latents to Wires: Surgical Post-Editing on Large Language Models
Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4
Given a large language model (LLM), can whoever holds the weights name a semantic target (e.g., the model's identity), locate the model components that produce it, and edit them so…
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models
Dongdong Yang, Deyue Zhang, Zhao Liu +5
Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly…
ElephantAgent: Contextual State Continuity in Agentic Systems
Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4
Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory. However, these external dependencies introduce novel attack surfaces. Recen…
Robust Privacy: Inference-Stage Privacy through Certified Robustness
Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4
An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data. The infe…
Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budget
Jiankai Jin, Chitchanok Chuengsatiansup, Toby Murray +3
Current implementations of differentially-private (DP) systems either lack support to track the global privacy budget consumed on a dataset, or fail to faithfully maintain the stat…
Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness
Jiankai Jin, Olga Ohrimenko, Benjamin I. P. Rubinstein
Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as…
Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems
Jiankai Jin, Eleanor McMurtry, Benjamin I. P. Rubinstein +1
Differential privacy is a de facto privacy framework that has seen adoption in practice via a number of mature software platforms. Implementation of differentially private (DP) mec…