Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of detecting software vulnerabilities, but lack of reasoning data hinders their ability to capture underlying vulnerability patterns. |
| Approach: | They propose a framework that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. |
| Outcome: | The proposed framework improves on SVEN and PrimeVul datasets and improves 12.24%-22.77% accuracy. |
Similar Papers
RealVul: Can We Detect Vulnerabilities in Web Applications with LLM? (2024.emnlp-main)
Copied to clipboard
| Challenge: | a lack of research specifically focused on vulnerabilities in the PHP language hinders the model’s ability to effectively capture the characteristics of specific vulnerabilities. |
| Approach: | They propose a framework that can isolate potential vulnerability triggers while streamlining code and eliminating unnecessary semantic information. |
| Outcome: | The proposed framework can isolate potential vulnerability triggers while streamlining the code and eliminating unnecessary semantic information. |
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing CodePre-trained models struggle to generalize due to superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities. |
| Approach: | They propose a framework that integrates multi-task learning with Large Language Models to effectively mine deep-seated vulnerability features. |
| Outcome: | The proposed framework surpasses seven state-of-the-art models in effectiveness, generalization, and robustness. |
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have a high vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. |
| Approach: | They propose to use large language models to test their security against jailbreak attacks that leverage crafted prompts to generate malicious outputs. |
| Outcome: | The proposed model is based on 320 manually crafted malicious code generation requirements, covering 11 jailbreak methods and 29 code functionality categories. |
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve security of LLM generated code are ineffective and lack localized regions of code. |
| Approach: | They propose a method for distilling a preference dataset of insecure and secure code pairs from frontier LLMs and a security reasoning that explains the issues and the fix. |
| Outcome: | The proposed method reduces code insecurity while improving overall code quality. |
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning (2026.findings-acl)
Copied to clipboard
Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang
| Challenge: | Large language model (LLM)-integrated applications face security vulnerabilities from prompt injection (PI) attacks. |
| Approach: | They propose a model enhancement method that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning to enable LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. |
| Outcome: | The proposed method outperforms baselines in three critical dimensions while maintaining utility performance without degradation. |
VerilogLAVD: LLM-Aided Pattern Generation for Verilog CWE Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing static analysis tools focus on functional correctness and depend heavily on manual rules. |
| Approach: | They propose a framework that generates executable Traversal Detection Patterns (TDPs) to help detect hardware vulnerabilities. |
| Outcome: | The proposed framework improves the F1 score by 133% compared to LLM-based methods. |
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation. |
| Approach: | They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement. |
| Outcome: | The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase. |
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent studies have focused on poisoning during supervised fine-tuning, RLHF, or inference-time time optimization. |
| Approach: | They propose a simple fake reward attack that requires no access to the reward model and significantly increases vulnerability. |
| Outcome: | The proposed attack reduces the fake reward ASR from 0.23 to 0.07 without degrading utility. |
Course-Correction: Safety Alignment Using Synthetic Preferences (2024.emnlp-industry)
Copied to clipboard
Rongwu Xu, Yishuo Cai, Zhenhong Zhou, Renjie Gu, Haiqin Weng, Liu Yan, Tianwei Zhang, Wei Xu, Han Qiu
| Challenge: | Recent studies show that large language models generate harmful content, but the potential for generating harmful content is an escalating concern. |
| Approach: | They propose to fine-tune LLMs with preference learning to emphasize the preference for timely course-correction by using an automated pipeline. |
| Outcome: | The proposed model improves course-correction skills without affecting general performance and resists jailbreak attacks. |
AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models (2024.findings-emnlp)
Copied to clipboard
Jiale Cheng, Yida Lu, Xiaotao Gu, Pei Ke, Xiao Liu, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Large Language Models (LLMs) exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks. |
| Approach: | They propose a framework to automatically expose weaknesses in Large Language Models (LLMs) they use three LLM-powered agents to perform comprehensive weakness identification . |
| Outcome: | The proposed framework shows that it is more effective than untargeted data augmentation methods like Self-Instruct to identify weaknesses in LLMs. |