arXiv subjects

Jinze Gu

Publications and source records attributed to Jinze Gu.

3 recordsLinked to original sources

arXiv2026

When Debate Amplifies Risk: Social-Bias Vulnerabilities in Multi-Agent Safety Deliberation

Retrieval-augmented Web applications increasingly employ multi-agent debate (MAD) to aggregate conflicting, noisy, and heterogeneous information, yet deliberation is fundamentally a social process susceptible to interpersonal dynamics. When retrieved Web sources contain latent hazards alongside safe factual content, social biases such as conformity pressure and authority deference can override evidence-grounded safety boundaries. In this work, we investigate whether the social structure of deliberation can paradoxically amplify latent Web safety risks. We introduce SafeConflict-Bias, a controlled counterfactual diagnostic protocol spanning six core Web risk categories, which holds queries and retrieved evidence strictly invariant while isolating conversational majority sway, authority cues, and confidence asymmetry. Empirical evaluation across diverse proprietary and open-source backbones reveals that while isolated models reliably reject unsafe guidance, standard MAD catastrophically capitulates to social pressure---surging unsafe adoption from 0.0\% up to 100.0\% and systematically silencing safe minority evidence. To resolve this systemic fragility without retraining or debate regeneration, we propose RiskTrace-Debias, an inference-time auditing framework uniting evidence-first precommitment, social-metadata masking, and consistency-gated arbitration. RiskTrace-Debias suppresses worst-case unsafe adoption to $\le 2.0\%$ across all architectures without inducing over-refusal, while generating verifiable provenance traces to audit interpersonal manipulation in Web deliberation.

cs.CR↗

arXiv2026

GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction

Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge graphs into the retrieval pipeline, enabling LLMs to access entities, relations, and multi-hop dependencies encoded in structured knowledge. However, the same structured knowledge that empowers Graph RAG also creates a new privacy attack surface. We demonstrate that Graph RAG systems can be turned into structural oracles: through adaptive black-box interactions, an adversary can elicit sufficient relational evidence to reconstruct substantial portions of the hidden knowledge graph. We propose a structure-oriented reconstruction framework that recovers targeted graphs from both local and global perspectives. Specifically, Depth-Wise Heuristic Search extracts fine-grained node attributes by recursively expanding entity-centered evidence, while Breadth-Wise Diffusion Search infers graph topology by propagating across relation-induced neighborhoods. Experiments on generic and healthcare scenarios demonstrate that our method can recover over 90\% of the original knowledge graph from representative Graph RAG systems, revealing sensitive entities, relations, and structural dependencies with high fidelity. Existing guradrails provide limited defense against our attack, highlighting the inherent difficulty of safeguarding structural privacy in Graph RAG pipelines.

cs.CR↗

arXiv2026

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversaries can inject malicious or misleading knowledge that corrupts downstream reasoning and leads to harmful outcomes. Existing knowledge editing benchmarks primarily focus on editing efficacy and lack a unified framework for systematically evaluating the safety implications of edited knowledge on reasoning behavior. To address this gap, we present EditRisk-Bench, a benchmark for systematically evaluating safety risks of knowledge-intensive reasoning under malicious knowledge editing. Unlike prior benchmarks that mainly emphasize edit success, generalization, and locality, EditRisk-Bench focuses on how injected knowledge affects downstream reasoning behavior and reliability. It integrates diverse malicious scenarios, including misinformation, bias, and safety violations, together with multi-level knowledge-intensive reasoning tasks and representative editing strategies within a unified evaluation framework measuring attack effectiveness, reasoning correctness, and side effects. Extensive experiments on both open-source and closed-source LLMs show that malicious knowledge editing can reliably induce incorrect or unsafe reasoning while largely preserving general capabilities, making such risks difficult to detect. We further identify several key factors influencing these risks, including edit scale, knowledge characteristics, and reasoning complexity. EditRisk-Bench provides an extensible testbed for understanding and mitigating safety risks in knowledge editing for LLMs.

cs.AI↗