cs.AINov 2, 2026

Auditing Representation-Space Fraud Detection: A Bayesian IRL Framework for Calibrated Uncertainty and Its Limits

Authors: Shivam Swarup, Divya Prakash Shrivastava, Rakesh Thakur

Organizations: JAIN University (Deemed-to-be), Bengaluru, India · Zayed University, Dubai, UAE

Abstract

Shilling detectors for recommender systems are almost always evaluated by one number, detection AUROC, with no account of when it can be trusted. We audit representation-space detection with VEIL (Variational Evaluation via Inverse-reinforcement Learning), a pairwise (Bradley-Terry) Bayesian reward-inference framework over frozen encoder embeddings, following the Bayesian auditing paradigm for LLM alignment [1]: (A) a base posterior; (B) a hierarchical ARD extension with learned confidence; and (C) a label-routed organic/attacker mixture used as an evidence-accumulation check.We prove (Proposition 1) that no detector built on a representation invariant to a transformation of user profiles can outperform chance against an attack that is indistinguishable from organic profiles under that invariance.Detection is near-perfect against synthetic-structure attacks (AUROC 0.936-1.000) but collapses under donor-mimicry, which clones a real user's item set and splices in 1-3 target items. Performance falls to chance on MovieLens-1M (0.48-0.51), partially degrades on Amazon Musical Instruments, and degrades least on CiaoDVD.Donor-mimicry is not undetectable: a non-learned baseline, based on each profile's maximum raw item-set Jaccard similarity to any other profile, reaches AUROC 0.92-0.97 (average precision 0.50-0.57) on all four donor-mimicry configurations, including ML-1M, where every embedding-based score is at chance.The signal is present in the raw profiles, but LightGCN's representation discards it, placing injected profiles closer to their true donor than its zero-propagation MF reduction does (distance 1.98 vs. 3.09). Severity varies by dataset, encoder, and detection method, with no single axis predicting the others. The limit lies in the representation, not the attack, and raw-similarity checks are a necessary complement to any learned detector.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 9, 2026

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method that audits bias in hidden-state representations across related model variants, for example before and after fine-tuning. Because fine-tuning reshapes representation geometry, absolute hidden states are not directly comparable, so we encode each sentence by its similarities to a fixed set of anchor sentences, yielding relative representations in a shared comparison space. There we measure how target groups shift in their association with positive and negative attributes, a quantity we call the Representational Bias Shift ΔBΔB. Across three model families and the WildGuardMix, DecodingTrust and ToxiGen benchmarks, ΔBΔB correlates with output-level bias change in 15 of the 18 settings we test, reaching ∣r∣=0.84|r| = 0.84 (p<0.001p < 0.001) under full fine-tuning and becoming more model-dependent under parameter-efficient adaptation. Thresholding ΔBΔB detects checkpoints whose bias increased with ROC AUC between 0.650.65 and 0.990.99, and on WildGuardMix and DecodingTrust it separates them better than a SEAT-based baseline for all three families. ΔBΔB is also stable under changes to the anchor set, attribute sets and target templates. Our method requires no task-specific evaluation data and audits a model in about three minutes, using 33-50×50\times less compute than the output-level benchmarks considered here. We view it as complementary to output-based auditing rather than a replacement for it.
Oct 15, 2026

Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems

Language embeddings are increasingly used in recommenders to represent item content, but their privacy risks remain poorly understood. We study whether item embeddings can reveal item identities when an adversary has access to auxiliary item text from external sources. We show that a simple cosine-similarity attack can recover item identities with high mean reciprocal rank across language models and candidate-set settings on two real-world datasets. Leakage is strongest when the adversary's partial information overlaps with the victim representation, but it also persists through semantic alignment between independently sourced descriptions. We further show that item leakage can propagate to user re-identification from sparse ratings. Finally, we evaluate obfuscated descriptions as a mitigation and find a clear leakage-utility tradeoff.
Aug 8, 2026

Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders

Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OBS) and hidden representation shift (IBS), measured through controlled counterfactual identity probes across gender, age, and race. Their relationship is summarized via Representation-Output Alignment (ROA), with quadrant diagnostics for identifying user-level hidden-output mismatch. Applied to six open-weight LLM families across three domains, FairGap reveals pervasive hidden-output decoupling: ROA rarely exceeds 0.22, and a non-negligible user population shows stable outputs despite substantial internal shifts, a mode that output-only audits cannot detect by design. Further, activation steering that reduces IBS by up to 8x simultaneously worsens OBS, demonstrating a fundamental tension between internal and output-level fairness that existing frameworks are unequipped to diagnose.