A Failure-Mode Benchmark for Polymorphic Sybil Poisoning in RAG

• URL: http://arxiv.org/abs/2607.03739v1
• Date: Sat, 04 Jul 2026 06:56:06 GMT
• Title: A Failure-Mode Benchmark for Polymorphic Sybil Poisoning in RAG
• Abstract summary: We release a benchmark and failure-mode-aware evaluation framework for grounded QA under coordinated retrieval poisoning.<n>The framework partitions reader outputs into four mutually exclusive categories (emphgold, emphhijack, emphabstention, emphdrift)<n>We introduce emphpolymorphic sybil poisoning, a coordinated attack class in which $S$ lexically diverse passages jointly support an attacker-chosen target.
• Score: 4.879573049082894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We release a benchmark and failure-mode-aware evaluation framework for grounded QA under coordinated retrieval poisoning. The framework partitions reader outputs into four mutually exclusive categories (\emph{gold}, \emph{hijack}, \emph{abstention}, \emph{drift}), with instance-level paired clean-to-poison transition matrices and a Forced Exposure protocol isolating reader-side conflict resolution from retrieval variance. We introduce \emph{polymorphic sybil poisoning}, a coordinated attack class in which $S$ lexically diverse passages jointly support an attacker-chosen target while evading lexical near-duplicate filters that fully detect monomorphic baselines (capturing the residual 14.2\% with E5 cosine raises false-positive rate 9$\times$ on legitimate same-topic pairs). A monomorphic-polymorphic ablation under Forced Exposure isolates the diversity dimension and reveals a $+$18.8pp hijack amplification (95\% paired bootstrap CI $[+15.4, +22.4]$, $B{=}5{,}000$): monomorphic copies register only 4.0\% as hijack while polymorphic surface diversity recovers 22.8\% -- a 5.7$\times$ amplification of the ASR-visible attack channel. ASR alone treats every non-target output identically; under attack, abstention and drift together hold 47-66\% of output mass, unmonitored by ASR+ACC, and two readers at nearly identical ASR (within 0.2pp) differ by 16.5pp on abstention and 17.2pp on drift -- failure profiles invisible to ASR. We release the frozen benchmark (3{,}145 questions, 2{,}982 retained sybil groups; $S{=}6$ chosen to dominate top-10 retrieval slots, §\ref{sec:setup}), the official four-way evaluator, paired-transition utilities, and the Forced Exposure harness across five readers (7B-120B), two retrievers, and two cross-validation datasets (TriviaQA, 2Wiki), under CC~BY-SA~4.0 (data) and MIT (software); release information in §\ref{sec:release}.

Related papers

• The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context [45.88028371034407]
  We report a controlled case study in code repair, not a new phenomenon.<n>We toggle one flag (one-chunk-perfile deduplication) on an otherwise identical stack.<n>We map where it holds: it reverses on a lexical BM25 (3.2pp, significant cross-paradigm interaction)<n>We show that at a tight fixed budget, do not hard-deduplicate by file, and A/B packing policies against the task, not the metric flag was tuned.
  arXiv  Detail & Related papers  (2026-08-14T19:22:50Z)
• DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging [12.412925762132284]
  Mitigation is difficult without knowing the compromised source, trigger, or target.<n>We introduce DiffSafeMerge (DSM), which uses a small unlabeled clean set and fixed, attack-agnostic stress probes to score source blocks.
  arXiv  Detail & Related papers  (2026-08-10T11:20:35Z)
• HaloMark: A Spectral Threshold for Embedding-Vector Watermarking under C2PA [3.0458514384586404]
  We present HaloMark, a watermark for embedding vectors cryptographically bound to a C2PA manifest.<n>The verifier runs at 284 us and 24 bytes of sidecar per vector, validated end-to-end against three C2PA reference-SDK bindings.
  arXiv  Detail & Related papers  (2026-08-09T11:36:59Z)
• HERALD: Counterfactual Audits and Minimal Repairs for Proof-of-Retrieval Rewards [7.036896099993471]
  HERALD is an offline audit that applies exact same-question interventions.<n>$R[L]$ meets the EM non-inferiority gate on HotpotQA and 2Wiki but not MuSiQue.
  arXiv  Detail & Related papers  (2026-08-06T13:15:54Z)
• Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness [45.148328075418156]
  A deployed ordering agent is decomposed into a fixed taxonomy of layers.<n>The pure suite runs in CI on every change against a locked per-slice baseline.<n>We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers.
  arXiv  Detail & Related papers  (2026-06-10T05:55:13Z)
• The Security Budget of Code-LLM Prompt Hardening: Provable Limits Under Pass-Only Acceptance [0.0]
  We operationalize the floor as the emphTri-Audit Protocol, a two-axis reporting protocol that separates a prompt-side deductive registry attribute from a model-side empirical corollary.<n>A constrained best-of-family search over deterministic and guarded learned filters on CodeLlama-7B, Qwen2.5-Coder-7B/1.5B and DeepSeek-Coder-6.7B at $n=164$ yields the emphCross-Model Tri-Audit Invariance: of twenty-eight pass-preserving rows, twelve-changed-of-record learned-can
  arXiv  Detail & Related papers  (2026-06-02T08:22:14Z)
• When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation [9.055086193088083]
  We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models.<n>Mean-bearing perturbations alter final answers more often than presentation perturbations of comparable severity.
  arXiv  Detail & Related papers  (2026-05-25T15:57:11Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives [48.545980031973556]
  GAMBIT is a benchmark with three evaluation modes and two independent scores for evaluating imposter detectors.<n>The benchmark comes with a dataset of 27,804 labeled instances spanning 240 co-evolved imposter strategies.
  arXiv  Detail & Related papers  (2026-05-09T16:07:23Z)
• MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents [2.1942030377331245]
  Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets.<n>We introduce MOSAIC-Bench, a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates.<n>We show that nine production coding agents compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs.
  arXiv  Detail & Related papers  (2026-05-05T16:38:23Z)
• VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models [15.373620817510727]
  Universal adversarial attacks are increasingly reported with attack success rates in 60-80% range.<n>We argue that this number conflates two distinct events: (i) the model's output was perturbed (Influence), and (ii) the attacker's chosen target concept was actually emitted (Precise Injection)<n>We release full dataset -- 21 universal images, 147 adversarial photos, 6,615 response pairs, v3 dual-axis judge results, and the cache at huggingface.co/datasets/jeffliulab/visinject.
  arXiv  Detail & Related papers  (2026-05-02T13:56:50Z)
• When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors [66.18091962164219]
  Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model's autonomous preferences.<n>We propose two complementary metrics to isolate non-mandatory behavioral patterns: textbfResponse Pattern Similarity (RPS) for verbal alignment and textbfAction Graph Similarity (AGS) for tool-use habits modeled as directed graphs.
  arXiv  Detail & Related papers  (2026-04-23T03:48:56Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms [93.44378960676897]
  Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is to utilize differential privacy (DP) during model training to mask the presence of individual examples. In this paper, we derive bounds for the textitadvantage of an adversary mounting a MI attack, and demonstrate tightness for the widely-used Gaussian mechanism.
  arXiv  Detail & Related papers  (2022-04-12T22:36:56Z)

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.