ReCode is introduced, a compositional budget-efficient attack that combines desensitization rewriting with two effective low-cost primitives identified by Fair-ASR, to provide a comparable evaluation basis for black-box jailbreak attacks under shared target-call budgets B.
Abstract
Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods. Existing compute-aware evaluations reduce heterogeneous resources into FLOPs, which is difficult to estimate for black-box models and fails to capture resource-specific constraints. To provide a comparable evaluation basis, we introduce Fair-ASR, an evaluation protocol for black-box jailbreak attacks under shared target-call budgets B, using target calls as a directly observable and method-agnostic comparison axis while tracking attacker calls separately for efficiency analysis. We re-evaluate 11 representative attacks under the Fair-ASR protocol and find that attack rankings change substantially across target-call budgets, simple stochastic perturbations and hand-crafted templates remain highly competitive under equal target access, and no evaluated LLM-driven method is efficient in both target and attacker calls. Motivated by this efficiency gap, we introduce ReCode, a compositional budget-efficient attack that combines desensitization rewriting with two effective low-cost primitives identified by Fair-ASR. Under a budget of 20 target calls, ReCode achieves 85% ASR on GPT-5 while requiring only 7.19 attacker calls per request on average, showing strong efficiency in both target and attacker calls.
It is found that defenses rarely improve downstream capability, but instead vary in how they trade safety gains against usability and efficiency as well as performance impact, over-refusal on benign inputs, and inference cost.
The results show that access to repository history is insufficient: concealment becomes most effective when benign and malicious changes jointly occupy the auditor's active review context or when the stated purpose plausibly accounts for the attack-bearing diff.
Defenses against jailbreak attacks on Large Language Models (LLMs) operate at different pipeline stages, such as input modification or output guard, but it remains unclear which defenses to deploy at each stage and how to combine them. Prior empirical studies, fragmented by inconsistent attack-success-rate definitions and experimental settings, have evaluated defenses largely in isolation. Here we present the first systematic study, to our knowledge, of defense combinations both within and across pipeline stages, under a consistent threat model of direct, black-box, single-turn attacks. Our decision framework standardizes evaluation through a principled attack-success-rate formulation with controlled query budgets, together with explicit fairness rules. Across 19 attacks and 15 defenses, we find that no single defense is universally best, but well-chosen combinations achieve substantial safety with minimal utility degradation, yielding practical recommendations for layered defense pipelines.
This work presents Porting Benchmark, a curated dataset of 1,234 security patch backporting cases spanning cross-version, cross-branch, and cross-repository scenarios, paired with a common evaluation framework and identifies four root-cause categories (missing target API awareness, cross-version semantic mismatch, non-local dependency propagation failure, and patch construction or localization failure) and derive concrete directions for next-generation tool design.
Jincheng Yang, Yulong Fu, Chengwei Liu et al.· 0 citations
Prompt-injection detectors are typically evaluated using aggregate <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> on in-distribution test data, which offers limited insight into behavior under distribution shift, particularly on the benign side of the decision boundary, where false positives impose direct operational cost yet are seldom measured. We present PIDS-Bench, a frozen multi-axis benchmark that jointly evaluates attack detection and benign false-positive behavior at fixed thresholds, spanning in-distribution inputs, hard-benign prompts that mimic injection structure without malicious intent, obfuscated attacks, and domain and structural distribution shifts. We evaluate seven detectors (learned baselines, external prompt-injection classifiers, and broad-safety comparators) alongside a rule-based lower-bound reference. Multi-axis evaluation exposes a failure mode that aggregate <inline-formula> <tex-math notation="LaTeX">$F_{1}$ </tex-math></inline-formula> conceals. A detector exceeding <inline-formula> <tex-math notation="LaTeX">$F_{1} = 0.98$ </tex-math></inline-formula> on the held-out split still misclassifies roughly one-third of an externally-sourced benign subset drawn from public corpora and restricted to security-adjacent content. Across a full threshold sweep and five training seeds, no internal detector reaches an operating point satisfying <inline-formula> <tex-math notation="LaTeX">$F_{1} \geq 0.95$ </tex-math></inline-formula> and hard-benign <inline-formula> <tex-math notation="LaTeX">$\mathrm {FPR} \leq 0.10$ </tex-math></inline-formula> together on this stress distribution. Decomposing by provenance, we find that hard-negative augmentation nearly eliminates over-defense on curated stress inputs but leaves it substantially intact on externally-sourced prompts, a pattern we term provenance-sensitive over-defense. The asymmetry holds across both fine-tuned architectures and does not diminish as the augmentation pool grows, with the externally-sourced FPR remaining far above the 0.10 target. Whether augmentation matched to the externally-sourced distribution would close this gap is untested; threshold calibration and curated-style augmentation alone do not.
Yusuf Khalid Shire, Sang-Chul Kim· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
