Imagen de Portada

Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Tony T., Hughes, John, Sleight, Henry, Schaeffer, Rylan, Agrawal, Rajashree, Barez, Fazl, Sharma, Mrinank, Mu, Jesse, Shavit, Nir, Perez, Ethan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Best-of-N Jailbreaking
por: Hughes, John, et al.
Publicado: (2024)

Chain-of-Thought Hijacking
por: Zhao, Jianli, et al.
Publicado: (2025)

Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
por: Schaeffer, Rylan, et al.
Publicado: (2024)

Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
por: Peng, Alwin, et al.
Publicado: (2024)

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
por: Youstra, Jack, et al.
Publicado: (2025)

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
por: Fu, Tingchen, et al.
Publicado: (2024)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
por: Chaudhary, Maheep, et al.
Publicado: (2025)

Understanding Addition in Transformers
por: Quirke, Philip, et al.
Publicado: (2023)

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness
por: Fu, Tingchen, et al.
Publicado: (2025)

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
por: Cunningham, Hoagy, et al.
Publicado: (2026)

Query Circuits: Explaining How Language Models Answer User Prompts
por: Wu, Tung-Yu, et al.
Publicado: (2025)

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
por: Gerstgrasser, Matthias, et al.
Publicado: (2024)

Rethinking AI Cultural Alignment
por: Bravansky, Michal, et al.
Publicado: (2025)

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models
por: Lan, Michael, et al.
Publicado: (2023)

Understanding Addition and Subtraction in Transformers
por: Quirke, Philip, et al.
Publicado: (2024)

Token Taxes: mitigating AGI's economic risks
por: Irwin, Lucas, et al.
Publicado: (2026)

Large Language Models Relearn Removed Concepts
por: Lo, Michelle, et al.
Publicado: (2024)

VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models
por: Gupta, Aman, et al.
Publicado: (2025)

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
por: Neo, Clement, et al.
Publicado: (2024)

Learning to Interpret Weight Differences in Language Models
por: Goel, Avichal, et al.
Publicado: (2025)

Forbidden Facts: An Investigation of Competing Objectives in Llama-2
por: Wang, Tony T., et al.
Publicado: (2023)

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
por: Marks, Luke, et al.
Publicado: (2024)

Do Sparse Autoencoders Generalize? A Case Study of Answerability
por: Heindrich, Lovis, et al.
Publicado: (2025)

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
por: Schrodi, Simon, et al.
Publicado: (2025)

Visualizing Neural Network Imagination
por: Wichers, Nevan, et al.
Publicado: (2024)

On the Complexity of Neural Computation in Superposition
por: Adler, Micah, et al.
Publicado: (2024)

Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space
por: Bebchuk, Alon, et al.
Publicado: (2026)

In-Context Learning of Energy Functions
por: Schaeffer, Rylan, et al.
Publicado: (2024)

NeuroADDA: Active Discriminative Domain Adaptation in Connectomic
por: Sawmya, Shashata, et al.
Publicado: (2025)

Testing the Limits of Jailbreaking Defenses with the Purple Problem
por: Kim, Taeyoun, et al.
Publicado: (2024)

Scalable Energy-Based Models via Adversarial Training: Unifying Discrimination and Generation
por: Yin, Xuwang, et al.
Publicado: (2025)

Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
por: Wen, Jiaxin, et al.
Publicado: (2024)

Embodied AI: Emerging Risks and Opportunities for Policy Action
por: Perlo, Jared, et al.
Publicado: (2025)

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
por: Oozeer, Narmeen, et al.
Publicado: (2025)

Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer
por: Simhi, Adi, et al.
Publicado: (2025)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
por: Oldfield, James, et al.
Publicado: (2025)

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
por: Li, Changyi, et al.
Publicado: (2026)

Scaling sparse feature circuit finding for in-context learning
por: Kharlapenko, Dmitrii, et al.
Publicado: (2025)

Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
por: Schaeffer, Rylan, et al.
Publicado: (2025)

Forecasting Rare Language Model Behaviors
por: Jones, Erik, et al.
Publicado: (2025)