Papers by Zhenhua Han

10 papers
MalURLBench: A Benchmark Evaluating Agents’ Vulnerabilities When Processing Web URLs (2026.findings-acl)

Copied to clipboard

Challenge: Existing models struggle to detect elaborately disguised malicious URLs, despite their ability to process malicious URL's.
Approach: They propose a benchmark to evaluate LLMs’ vulnerabilities to malicious URLs and a lightweight defense module to mitigate the vulnerability.
Outcome: The proposed framework analyzes 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites.
CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fingerprinting model ownership traces are vulnerable to illegal plagiarism and are not reliable.
Approach: They propose a rule-driven fingerprinting framework that encodes contextual correlations across multiple dialogue turns.
Outcome: The proposed framework achieves stronger stealth and robustness than previous work.
AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing (2026.findings-acl)

Copied to clipboard

Challenge: Existing LLMs lack immersion and adaptability, resulting in limited character orchestration and on-the-fly character introduction.
Approach: They propose an LLM-based framework that allows actors to interact with users in an ongoing narrative.
Outcome: The proposed framework outperforms commercial LLMs in character consistency, environment grounding, and narrative coherence.
EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint (2025.emnlp-main)

Copied to clipboard

Challenge: Existing fingerprinting methods require impractical white-box access or introduce detectable statistical anomalies.
Approach: They propose a gray-box fingerprinting framework that ensures stealthy and robust model provenance tracing.
Outcome: The proposed framework is the first to repurpose Membership Inference Attacks (MIAs) for defensive use, embedding ownership signals via memorization instead of artificial trigger-output overfitting.
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach: They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome: The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.
Web Fraud Attacks Against LLM-Driven Multi-Agent Systems (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Model (LLM)-driven multi-agent systems (MAS) are rapidly gaining popularity, and its inherent security risks are rapidly becoming a concern.
Approach: They propose a novel attack manipulating unique structures of web links to deceive MAS by using homoglyph deception, sub-directory nesting, and parameter obfuscation.
Outcome: The proposed attacks exploit unique structures of web links to deceive MAS . they exhibit significant destructive potential across different MAS architectures .
PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancement (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing black-box fingerprinting techniques rely on overfitting high-perplexity trigger patterns . experimental results show that model editing in the fingerprint domain exhibits unique advantages .
Approach: They propose a prefix-enhanced fingerprint editing framework that encodes copyright information into parameter offsets through dual-channel knowledge edit to achieve covert embedding of fingerprint features.
Outcome: The proposed model editing framework achieves 90% trigger precision in mainstream architectures . the proposed model editor achieves the 90% accuracy in mainstream models .
MEraser: An Effective Fingerprint Erasure Approach for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have raised critical concerns about model ownership and intellectual property protection.
Approach: They propose a method for effectively removing backdoor-based fingerprints from LLMs . they propose deleting backdoor fingerprints using a transferable erasure mechanism .
Outcome: The proposed method removes backdoor-based fingerprints while maintaining model performance.
Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models (2025.findings-emnlp)

Copied to clipboard

Challenge: lightweight plug-and-play framework that encodes backdoor fingerprints into LoRA adapters .
Approach: proposed framework encodes backdoor fingerprints into LoRA adapters via constrained fine-tuning . enables seamless fingerprint transplantation through parameter fusion, eliminating full-parameter updates while maintaining integrity.
Outcome: The proposed framework achieves superior robustness against various scenarios while reducing computational overhead compared to traditional approaches.
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Copied to clipboard

Challenge: Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach: They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome: The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations