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

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

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

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.

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