arXiv Machine Learning
Jun 4
Sequential Data Poisoning in LLM Post-Training
arXiv:2606. 04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.
Data-Poisoning Audits for Causal Effect Estimation
arXiv:2607. 19692v1 Announce Type: cross Abstract: Observational causal analyses increasingly pool records across sites, vendors, and collection systems, creating vulnerability to append-only attacks in which plausible records are strategically selected to alter a reported treatment effect.
Related stories
arXiv AI
Aug 11
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
arXiv:2608. 05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.
arXiv Machine Learning
Jun 17
Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
arXiv:2507. 20708v3 Announce Type: replace Abstract: The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing.
arXiv Machine Learning
Aug 4
Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
arXiv Machine Learning
Jul 27
Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness
arXiv:2607. 21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice.
arXiv Machine Learning
Jul 17
Causal Inference for Sequential Settings under Interference and Latent Confounding
arXiv:2607. 14940v1 Announce Type: new Abstract: We study causal inference under outcome interference for sequential, observational settings.
arXiv AI
Jun 15
Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents
arXiv:2606. 13884v1 Announce Type: new Abstract: Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors.
arXiv AI
Aug 7
Innovation-Residual Auditing of Autonomous Analysis Agents: Localization, Detection Limits, Error Control, and Identifiability
arXiv:2608. 05490v1 Announce Type: new Abstract: Autonomous agents now carry out entire data analyses, selecting cohorts, joining tables, and fitting models with little step-by-step supervision.
arXiv Machine Learning
Jul 10
Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration
arXiv:2607. 08122v1 Announce Type: new Abstract: Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic records.
arXiv AI
Jun 3
CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery
arXiv:2606. 03602v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the fundamental limitations of purely statistical methods, such as statistical distinguishability within equivalence classes and sensitivity to finite sample sizes.
arXiv Machine Learning
Aug 11
When Can Fraud Operations Authorize Automation? A Decision-Support Framework for Fresh Audit Evidence and Review Workload
arXiv:2608. 08577v1 Announce Type: new Abstract: Fraud operations must allocate events among automatic approval, analyst review, and automatic blocking even though the labels needed to evaluate these actions are selective and delayed.
arXiv Machine Learning
Jun 26
Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding
arXiv:2606. 27114v1 Announce Type: new Abstract: Uplift modeling, crucial for estimating individual treatment effects (ITE), faces dual challenges: flexibly leveraging inter-group similarity to enhance discriminative power and debiasing under unobserved confounding scenarios.