6 papers
RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
Ao Tian, Yunfeng Lu, Xinxin Fan +4
Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term,…
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
Changhao Wang, Yanfang Liu, Xinxin Fan +3
Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be ob…
TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement
Xinxin Fan, Wenxiong Chen, Quanliang Jing +4
Graph adversarial attacks are usually produced from the two perspectives of topology/structure and node feature, both of them represent the paramount characteristics learned by tod…
CAMA: Exploring Collusive Adversarial Attacks in c-MARL
Men Niu, Xinxin Fan, Quanliang Jing +2
Cooperative multi-agent reinforcement learning (c-MARL) has been widely deployed in real-world applications, such as social robots, embodied intelligence, UAV swarms, etc. Neverthe…
FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE
Wenbo Song, Xinxin Fan, Quanliang Jing +5
The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgen…
SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach
Shaoye Luo, Xinxin Fan, Quanliang Jing +4
Aiming at resisting backdoor attacks in convolution neural networks and vision Transformer-based large model, this paper proposes a generalized and model-agnostic trigger-purificat…