Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression

• URL: http://arxiv.org/abs/2511.22044v1
• Date: Thu, 27 Nov 2025 02:55:31 GMT
• Title: Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression
• Authors: Tianyu Zhang, Zihang Xi, Jingyu Hua, Sheng Zhong,
• Abstract summary: A lightweight model designed to predict the attack success rate (ASR) of adversarial prompts remains underexplored.<n>We propose a novel framework that incorporates an improved outline filling attack to achieve dense sampling of the model's security boundaries.<n> Experimental results show that our proxy model achieves an accuracy of 91.1 percent in predicting the relative ranking of average long response.
• Score: 10.64873345204336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the realm of black-box jailbreak attacks on large language models (LLMs), the feasibility of constructing a narrow safety proxy, a lightweight model designed to predict the attack success rate (ASR) of adversarial prompts, remains underexplored. This work investigates the distillability of an LLM's core security logic. We propose a novel framework that incorporates an improved outline filling attack to achieve dense sampling of the model's security boundaries. Furthermore, we introduce a ranking regression paradigm that replaces standard regression and trains the proxy model to predict which prompt yields a higher ASR. Experimental results show that our proxy model achieves an accuracy of 91.1 percent in predicting the relative ranking of average long response (ALR), and 69.2 percent in predicting ASR. These findings confirm the predictability and distillability of jailbreak behaviors, and demonstrate the potential of leveraging such distillability to optimize black-box attacks.

Related papers

• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling [50.872910438715486]
  Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting.<n>We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling.
  arXiv  Detail & Related papers  (2026-01-30T06:54:35Z)
• CS-GBA: A Critical Sample-based Gradient-guided Backdoor Attack for Offline Reinforcement Learning [7.5200963577855875]
  Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks.<n>We propose CS-GBA (Critical Sample-based Gradient-guided Backdoor Attack), a novel framework designed to achieve high stealthiness and destructiveness under a strict budget.
  arXiv  Detail & Related papers  (2026-01-15T13:57:52Z)
• ProvX: Generating Counterfactual-Driven Attack Explanations for Provenance-Based Detection [14.868358820809215]
  Provenance graph-based intrusion detection systems are deployed on hosts to defend against Advanced Persistent Threat.<n>Using Graph Neural Networks to detect these threats has become a research focus and has demonstrated exceptional performance.<n>We propose ProvX, an effective explanation framework for exlaining GNN-based security models on provenance graphs.
  arXiv  Detail & Related papers  (2025-08-08T07:12:10Z)
• Sampling-aware Adversarial Attacks Against Large Language Models [52.30089653615172]
  Existing adversarial attacks typically target harmful responses in single-point greedy generations.<n>We show that for the goal of eliciting harmful responses, repeated sampling of model outputs during the attack prompt optimization.<n>We show that integrating sampling into existing attacks boosts success rates by up to 37% and improves efficiency by up to two orders of magnitude.
  arXiv  Detail & Related papers  (2025-07-06T16:13:33Z)
• Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models [12.524811181751577]
  We propose a novel optimization for adversarial attacks against BCSD models.<n>In particular, we aim to improve the attacks in a challenging scenario, where the attack goal is to limit the model predictions to a specific range.<n>Our attack leverages the superior capability of black-box, model-agnostic explainers in interpreting the model decision boundaries.
  arXiv  Detail & Related papers  (2025-06-05T08:29:19Z)
• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models [79.76293901420146]
  Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. Our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
  arXiv  Detail & Related papers  (2024-07-15T23:41:11Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.