Imagen de Portada

Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ball, Sarah, Hasrati, Niki, Robey, Alexander, Schwarzschild, Avi, Kreuter, Frauke, Kolter, Zico, Risteski, Andrej
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Existing Large Language Model Unlearning Evaluations Are Inconclusive
por: Feng, Zhili, et al.
Publicado: (2025)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
por: Ball, Sarah, et al.
Publicado: (2024)

Antidistillation Sampling
por: Savani, Yash, et al.
Publicado: (2025)

Forcing Diffuse Distributions out of Language Models
por: Zhang, Yiming, et al.
Publicado: (2024)

Understanding and Mitigating Premature Confidence for Better LLM Reasoning
por: Gai, Jingchu, et al.
Publicado: (2026)

Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction
por: Ball, Sarah, et al.
Publicado: (2025)

A Simple and Effective Pruning Approach for Large Language Models
por: Sun, Mingjie, et al.
Publicado: (2023)

Rethinking LLM Memorization through the Lens of Adversarial Compression
por: Schwarzschild, Avi, et al.
Publicado: (2024)

Extrapolation by Association: Length Generalization Transfer in Transformers
por: Cai, Ziyang, et al.
Publicado: (2025)

Adversarial Attacks on Robotic Vision Language Action Models
por: Jones, Eliot Krzysztof, et al.
Publicado: (2025)

Antidistillation Fingerprinting
por: Xu, Yixuan Even, et al.
Publicado: (2026)

Benchmarking ChatGPT on Algorithmic Reasoning
por: McLeish, Sean, et al.
Publicado: (2024)

Adaptive Content Restriction for Large Language Models via Suffix Optimization
por: Li, Yige, et al.
Publicado: (2025)

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
por: Yuan, Chenchen, et al.
Publicado: (2026)

TOFU: A Task of Fictitious Unlearning for LLMs
por: Maini, Pratyush, et al.
Publicado: (2024)

Looking beyond the next token
por: Thankaraj, Abitha, et al.
Publicado: (2025)

Algorithms for Adversarially Robust Deep Learning
por: Robey, Alexander
Publicado: (2025)

Base Models Look Human To AI Detectors
por: Xu, Yixuan Even, et al.
Publicado: (2026)

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
por: Xu, Yixuan Even, et al.
Publicado: (2025)

From Ground Truth to Measurement: A Statistical Framework for Human Labeling
por: Chew, Robert, et al.
Publicado: (2026)

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
por: Huang, Allison, et al.
Publicado: (2024)

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
por: Zhai, Runtian, et al.
Publicado: (2023)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
por: Mu, Junjie, et al.
Publicado: (2025)

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
por: He, Yutong, et al.
Publicado: (2024)

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
por: Levin, Roman, et al.
Publicado: (2025)

Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
por: Kim, Minkyoung, et al.
Publicado: (2024)

AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers
por: Wuttke, Alexander, et al.
Publicado: (2024)

Reasoning Capabilities of Large Language Models on Dynamic Tasks
por: Wong, Annie, et al.
Publicado: (2025)

SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding
por: Zhang, Yazhou, et al.
Publicado: (2024)

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
por: McLeish, Sean, et al.
Publicado: (2025)

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
por: Ball, Sarah, et al.
Publicado: (2025)

Weight Ensembling Improves Reasoning in Language Models
por: Dang, Xingyu, et al.
Publicado: (2025)

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
por: Tang, Haochun, et al.
Publicado: (2026)

Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs
por: Cherepanova, Valeriia, et al.
Publicado: (2024)

Unnatural Languages Are Not Bugs but Features for LLMs
por: Duan, Keyu, et al.
Publicado: (2025)

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
por: Williams, Joshua Nathaniel, et al.
Publicado: (2024)

State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models
por: Wong, Annie, et al.
Publicado: (2026)

Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
por: Huang, Fan, et al.
Publicado: (2026)

Mimetic Initialization of MLPs
por: Trockman, Asher, et al.
Publicado: (2026)

Potemkin Understanding in Large Language Models
por: Mancoridis, Marina, et al.
Publicado: (2025)