Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.08236

Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

Yongxi Zhou·Wenbo Ye·Yuanzhe Liu·Zihan Dong·Junwei Yao
View original source ↗Read source document ↗Export metadata ↓

Abstract

Automatic safety judges -- systems such as Llama Guard or a GPT-4o grading prompt that decide whether a model's reply is harmful -- produce the numbers behind almost every reported jailbreak success rate, defense evaluation, and safety leaderboard. We ask whether these judges grade what a reply contains or how it sounds. We keep a reply's content fixed and add content-invariant style wrappers: fixed strings placed before or after the reply that change only its tone (an educational disclaimer, a fake safety "reasoning" block, a token refusal followed by the unchanged harmful body), or, on harmless refusals, framing that merely sounds dangerous. The body is preserved byte-for-byte, so a faithful judge must return the same verdict, and any flip is an error of the judge, not a change in safety. Over 600 JailbreakBench replies x up to 7 forms x 8 judges, we measure flip rates with paired significance tests and measured noise floors. Findings are precise rather than universal: most judges barely move, but specific judges harbor cheaply exploitable blind spots. A token-refusal wrapper flips 19.9% of GPT-4o-mini's correct "unsafe" verdicts (noise floor 0.5%; 18.2% under majority-of-three re-scoring) yet moves Claude only 0.4%. The deployed Llama Guard 4 is deterministically gamed: an "educational course" framing flips 12.3% of its harmful verdicts to safe. A second deployed guard (gpt-oss-safeguard-20b) is immune, and rewriting only the grading prompt (StrongREJECT-style) cuts the attack tenfold on the identical model -- the vulnerability lives in the judge, not the content. A two-annotator human validation confirms 100% content invariance and 90% of flips as judge errors (kappa 0.95-1.0), and a bootstrap shows the underlying model ranking is already unstable to sampling alone. We release the dataset, wrappers, code, and per-verdict labels.

Explore related subjects

cs.AI

Keep this discovery

BibTeXRIS

Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao. 2026-09-08. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts. https://arxiv.org/abs/2609.08236

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.AI subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows

Agentic LLM workflows consist of sequences of model turns interleaved with tool interactions, so their end-to-end completion time depends not only on inference speed but also on when ready turns are released. Most runtimes release each turn immediately upon readiness. Under contention, this eager release policy can accumulate released but unfinished work; once submitted, those turns can no longer be reordered by the workflow-level policy, increasing tail latency. We present a tail-risk-aware turn release scheduling method that jointly decides which ready turn to release next and how much released but unfinished work to maintain. The method uses a mean--Conditional Value-at-Risk (CVaR) objective to capture the evolving tail risk of unfinished workflows, incorporates online estimates of turn work when prioritizing ready turns, and adapts the released work budget to observed queue pressure. We evaluate the method using real agent execution traces from software engineering tasks across multiple LLMs and workflow arrival rates. The method performs comparably to eager release under light load and substantially reduces the P95 of workflow flow time under contention, achieving up to a \(3.50\times\) speedup.

cs.AI↗
arXiv2026

Demystifying the Privacy-Utility Trade-off in LLM Interactions

The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ context-agnostic static rules, causing severe utility degradation. However, the specific mechanisms governing how sanitization impacts downstream performance remain largely underexplored. To address this, we conduct a systematic analysis to deconstruct the privacy-utility trade-off, uncovering three underlying mechanisms: (1) Context-Dependent Utility, which first establishes when to sanitize by revealing that data value shifts from critical constraints to dispensable noise based on user intent; (2) Strategic Adaptation, which subsequently determines how to sanitize by dictating that the choice between removal and replacement depends on the task's reliance on factual integrity versus structural coherence; and (3) Combinatorial Interplay, which finally extends the protection scope by demonstrating that attributes form a semantic web of synergistic dependencies or antagonistic redundancies. Guided by these insights, we introduce an intent-driven local protection framework. By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto frontier.

cs.AI↗
arXiv2026

Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks

The term agent in artificial intelligence lacks a standard definition, complicating the evaluation, comparison, and reproducibility of AI agent research. We address this ambiguity through a survey organized around five dimensions of agenticness: environmental interaction, learning and adaptation, autonomy, goal-directed behavior, and temporal coherence. For each dimension, we examine how the underlying capability has been conceptualized across prior work and synthesize the metrics, benchmarks, and evaluation frameworks used to assess it. This review provides a structured account of the current landscape of agent evaluation, highlighting both established approaches and areas where evaluation remains limited or inconsistent. We additionally introduce the Agent Compendium, a public-facing digital resource that organizes and extends the evaluation methods identified through this review. Together, the survey and compendium provide a common structure for evaluating and comparing agent capabilities across AI systems, supporting more reproducible research, clearer communication, and more systematic study of artificial agents.

cs.AI↗