Latent Space Discontinuity Exploitation
Published Analyzed Source: arXiv
A vulnerability exists in certain Large Language Models and diffusion models due to discontinuities in their latent space, which arise from data sparsity during training. An attacker can craft inputs containing lexically rare or semantically ambiguous constructs to guide the model's inference process toward these unstable, poorly-conditioned regions. This technique, termed "Alignment Degradation Induction," can degrade or bypass safety alignment mechanisms. Through iterative, multi-turn…
Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks
Evaluated models: Not reported