mlsanityData to 7 Oct 2026

Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks

arXiv 2511.00346 ↗First posted 1 Nov 2025cs.CR cs.AI cs.LGcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

The rapid proliferation of Large Language Models (LLMs) has raised significant concerns about their security against adversarial attacks. In this work, we propose a novel approach to crafting universal jailbreaks and data extraction attacks by exploiting latent space discontinuities, an architectural vulnerability related to the sparsity of training data. Unlike previous methods, our technique generalizes across various models and interfaces, proving highly effective in seven state-of-the-art LLMs and one image generation model. Initial results indicate that when these discontinuities are exploited, they can consistently and profoundly compromise model behavior, even in the presence of layered defenses. The findings suggest that this strategy has substantial potential as a systemic attack vector.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 11 of its 15 references that are in the map. First posted on arXiv 1 Nov 2025.

Builds on

11 of 15 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs16 May
  2. 2025Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models30 Jan
  3. 2024Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models24 Dec
  4. 2024Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks27 Aug
  5. 2024Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models13 Jun
  6. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack2 Apr

Other references · 5

  1. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  2. 2024PLeak: Prompt Leaking Attacks against Large Language Model Applicationscited by 113
  3. 2024On Protecting the Data Privacy of Large Language Models (LLMs): A Surveycited by 91
  4. 2024Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillationcited by 21
  5. 2025JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Modelscited by 8

Built on by

Not cited yet.