惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

G
Google Developers Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
量
量子位
C
Check Point Blog
B
Blog RSS Feed
Y
Y Combinator Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
A
About on SuperTechFans
Microsoft Azure Blog
Microsoft Azure Blog
博
博客园 - 聂微东
阮一峰的网络日志
阮一峰的网络日志
人人都是产品经理
人人都是产品经理
小众软件
小众软件
Last Week in AI
Last Week in AI
博
博客园 - 【当耐特】
GbyAI
GbyAI
The Cloudflare Blog
博
博客园 - 叶小钗
S
SegmentFault 最新的问题
博
博客园 - Franky
Engineering at Meta
Engineering at Meta
F
Fortinet All Blogs
B
Blog
Jina AI
Jina AI

Proceedings of the AAAI Conference on Artificial Intelligence

Resource Efficient Sleep Staging via Multi-Level Masking and Prompt Learning AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research Modulation-Based Backdoors: Leveraging Amplitude and Frequency Patterns to Attack Speaker Recognition Learning Structurally Stabilized Representations for Lossless DNA Storage ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and Verification RTMol: Rethinking Molecule-text Alignment in a Round-trip View Physical-regularized Hierarchical Generative Model for Metallic Glass Structural Generation and Energy Prediction Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass Control RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment Transferring Causal Driving Patterns for Generalizable Traffic Simulation with Diffusion-Based Distillation TRACE: Transformation-Aware Graph Refinement for Reaction Condition Prediction SIDE: Surrogate Conditional Data Extraction from Diffusion Models DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoT ProAR: Probabilistic Autoregressive Modeling for Molecular Dynamics Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data VFCionX: Bridging Large and Small Models for Robust Vulnerability-Fixing Commit Identification T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures Topology-Enhanced and Label Correlation-Aware Model for Protein-Protein Interaction Prediction InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling NucEL: Single-Nucleotide ELECTRA-Style Genomic Pre-training for Efficient and Interpretable Representations OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning Learning from Long-Term Engagement: Adaptive Tutoring Dialogue Planning for Personalized Education Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing Multi-Horizon Time Series Forecasting of Non-Parametric CDFs with Deep Lattice Networks From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning Unveiling the Attribute Misbinding Threat in Identity-Preserving Models
CHASE: Contextual History for Adaptive and Simple Exploit...
Zhiqiang Hao · 2026-03-14 · via Proceedings of the AAAI Conference on Artificial Intelligence

Authors

  • Zhiqiang Hao Nanjing University
  • Chuanyi Li Nanjing University
  • Ye Fan China Mobile Communications Group Jiangsu Co., Ltd
  • Jun Cai Nanjing University
  • Xiao Fu Nanjing University
  • Shangqi Wang China Mobile Communications Group Jiangsu Co., Ltd
  • Hao Shen China Mobile Communications Group Jiangsu Co., Ltd
  • Jiao Yin China Mobile Communications Group Jiangsu Co., Ltd
  • Jidong Ge Nanjing University
  • Bin Luo Nanjing University
  • Vincent Ng University of Texas at Dallas

DOI:

https://doi.org/10.1609/aaai.v40i1.36996

Abstract

We propose Contextual History for Adaptive and Simple Exploitation (CHASE), a novel multi-turn method for Large Language Model (LLM) jailbreaking. Rather than directly attack an LLM that may be difficult to jailbreak, CHASE first collects jailbroken histories from an easy-to-jailbreak LLM and then transfers them to the target LLM. Through this history transfer process, CHASE misleads the target LLM into thinking that it is responsible for producing the jailbroken histories and increases the chances of successful jailbreaking by prompting it to continue the conversation. Extensive evaluations on mainstream LLMs show that CHASE consistently achieves higher attack success rates and demands fewer computational resources compared to existing methods.

How to Cite

Hao, Z., Li, C., Fan, Y., Cai, J., Fu, X., Wang, S., … Ng, V. (2026). CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 345–353. https://doi.org/10.1609/aaai.v40i1.36996

Issue

Section

AAAI Technical Track on Application Domains I

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。