Our papers “Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds”, “Machine Unlearning in Low-Dimensional Feature Subspace”, and “DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under Deceptive Injections” are accepted by NeurIPS 2026. Congratulations to Yaxin, Kun, and Li!
Our papers “LG-DCD: Evolution-Aware Local Differential Privacy for Dynamic Community Detection over Graphs”, “Feature Attribution in Directed Acyclic Graphs Using Edge Intervention”, “DaDaDa: A Dataset for Data Pricing in Data Marketplaces” and “Parallel Oblivious Acyclic Joins for TEE-based Encrypted Databases” are accepted by IEEE International Conference on Data Engineering (ICDE), 2027. Congratulations to Xinyue, Qiheng,…
Our papers “MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection”, “MAppPrint: Robust and Real-time Mobile App Fingerprinting via Traffic Behavior Causal Graphs”, and “Can a Single Message Paralyze the AI Infrastructure? The Rise of AbO-DDoS Attacks through Targeted Mobius Injection” are accepted by Network and Distributed System Security (NDSS) Symposium 2027. Congratulations to…
I start to serve as a senior editor on the editorial board of IEEE Transactions on Knowledge and Data Engineering (TKDE).
Our paper “PrivFDM: Differentially Private Federated Diffusion Models for Image Synthesis” is accepted by ACM Multimedia’2026. Congratulations to Wenbo!
A research project entitled “Privacy Agent for Agentic AI: Contextual Integrity, Differential Privacy and Beyond” has been awarded by Research Grant Council, HKSAR with HK$1,054,064 (2027-2029).
Our paper “LURE: Latent Space Unblocking for Multi-Concept Reawakening in Diffusion Models” is accepted by IJCAI’2026. Congratulations to Mengyu!
Our papers “Differentially Private Cross-Silo Recommendation from Implicit Feedback”, “Unlearning Isn’t Deletion: Investigating Reversibility of Machine Unlearning in LLMs”, and “On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression”, are accepted by International Conference on Machine Learning (ICML 2026). Congratulations to Xun, Xiaoyu and Xinwei!
Our paper “Hitchhiking on Inherent Randomness: Diffusion-based Graph Generation under Differential Privacy” is accepted by ACM CCS 2026. Congratulations to Renxuan!
Our papers “From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning” and “AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search” are accepted by Findings of the Association for Computational Linguistics (ACL). Congratulations to Xiaoyu and Yingbin!