AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
cs.AI, cs.CL, cs.CR
Submitted: 2026-11-05
Updated: 2026-11-13
Terminology
Sources
- LoRA: Low-Rank Adaptation of Large Language Models
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models
- LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes
- SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
- LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
- StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents