PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations
cs.AI, cs.CL, cs.CR
Submitted: 2026-09-24
Updated: 2026-09-25
Terminology
Sources
- The Llama 3 Herd of Models
- HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models
- Multi-step Jailbreaking Privacy Attacks on ChatGPT
- Scalable Extraction of Training Data from (Production) Language Models
- GPT-4 Technical Report
- A (More) Realistic Evaluation Setup for Generalisation of Community Models on Malicious Content Detection
- PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Prompt Injection attack against LLM-integrated Applications
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection