Related papers: Provable Performance Guarantees of Copy Detection Patterns

Related papers

Rigorous Security Proofs for Practical Quantum Key Distribution [0.0]
This thesis is concerned with rigorous security analyses of Quantum Key Distribution (QKD) protocols.<n>We establish a security proof for variable-length QKD protocols against IID collective attacks, and extend this result to coherent attacks using the postselection technique.<n>Second, we develop a method to bound phase error rates in entropic uncertainty relation-based and phase error rate-based proofs, using only the observed statistics of the protocol.<n>Third, we present a very general security analysis based on the marginal-constrained entropy accumulation theorem.
arXiv Detail & Related papers (2026-04-23T15:48:02Z)
Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
arXiv Detail & Related papers (2026-04-17T13:27:11Z)
Towards Anytime-Valid Statistical Watermarking [63.02116925616554]
We develop the first e-value-based watermarking framework, Anchored E-Watermarking, that unifies optimal sampling with anytime-valid inference.<n>Our framework can significantly enhance sample efficiency, reducing the average token budget required for detection by 13-15% relative to state-of-the-art baselines.
arXiv Detail & Related papers (2026-02-19T18:32:26Z)
BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search [72.87861928940929]
Boundary-Aware Policy Optimization (BAPO) is a novel RL framework designed to cultivate reliable boundary awareness without compromising accuracy.<n>BAPO introduces two key components: (i) a group-based boundary-aware reward that encourages an IDK response only when the reasoning reaches its limit, and (ii) an adaptive reward modulator that strategically suspends this reward during early exploration, preventing the model from exploiting IDK as a shortcut.
arXiv Detail & Related papers (2026-01-16T07:06:58Z)
Enhancing Trustworthiness with Mixed Precision: Benchmarks, Opportunities, and Challenges [12.438306093697]
Large language models (LLMs) have shown promising performance across various tasks.<n>LLMs' autoregressive decoding process poses significant challenges for efficient deployment on existing AI hardware.
arXiv Detail & Related papers (2025-11-27T14:17:43Z)
AI-Generated Image Detection: An Empirical Study and Future Research Directions [6.891145787446519]
Threats posed by AI-generated media, particularly deepfakes, are raising significant challenges for forensics.<n>Several forensic methods have been proposed, they suffer from three critical gaps.<n>These limitations hinder fair comparison, obscure true robustness, and restrict deployment in security-critical applications.
arXiv Detail & Related papers (2025-11-04T18:13:48Z)
ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search [69.60882125603133]
We present ReliabilityRAG, a framework for adversarial robustness that explicitly leverages reliability information of retrieved documents.<n>Our work is a significant step towards more effective, provably robust defenses against retrieved corpus corruption in RAG.
arXiv Detail & Related papers (2025-09-27T22:36:42Z)
Semi-Supervised Defect Detection via Conditional Diffusion and CLIP-Guided Noise Filtering [8.132909775584395]
This paper introduces a semi-supervised defect detection framework based on conditional diffusion (DSYM)<n>A conditional diffusion model synthesizes multi-scale pseudo-defect samples, while a CLIP cross-modal feature-based noise filtering mechanism mitigates label contamination.<n>This research provides a high-precision, low-labeling-dependent solution for defect detection in industrial quality inspection scenarios.
arXiv Detail & Related papers (2025-07-08T01:53:34Z)
Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health [14.256683587576935]
Only 9% of FDA-registered AI-based healthcare tools include a post-deployment surveillance plan.<n> Existing monitoring approaches are often manual, sporadic, and reactive.<n>We propose that the detection of changes in the data and model performance degradation should be framed as distinct statistical hypothesis testing problems.
arXiv Detail & Related papers (2025-06-06T03:04:44Z)
Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction [18.76704882926895]
Most existing detection methods focus excessively on detection accuracy, neglecting the societal risks posed by high false positive rates (FPRs)<n>This paper addresses this issue by leveraging Conformal Prediction (CP), which effectively constrains the upper bound of FPRs.<n>To overcome this trade-off, this paper proposes a Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction (MCP)
arXiv Detail & Related papers (2025-05-08T09:32:38Z)
Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation [52.83870601473094]
Embodied agents exhibit immense potential across a multitude of domains. Existing research predominantly concentrates on the security of general large language models. This paper introduces a novel input moderation framework, meticulously designed to safeguard embodied agents.
arXiv Detail & Related papers (2025-04-22T08:34:35Z)
Quantifying Robustness: A Benchmarking Framework for Deep Learning Forecasting in Cyber-Physical Systems [44.61435605872856]
We introduce a practical robustness definition grounded in distributional robustness, explicitly tailored to industrial CPS. Our framework simulates realistic disturbances, such as sensor drift, noise and irregular sampling, enabling thorough robustness analyses of forecasting models.
arXiv Detail & Related papers (2025-04-04T14:50:48Z)
Imperfect detectors for adversarial tasks with applications to quantum key distribution [0.0]
We develop a general framework for analysing imperfect threshold detectors. We treat uncharacterised device parameters such as dark counts and detection efficiencies as adversarially controlled within some ranges. Our results strengthen the connection between theoretical security and practical implementations.
arXiv Detail & Related papers (2025-03-08T19:53:18Z)
Noise-Adaptive Conformal Classification with Marginal Coverage [53.74125453366155]
We introduce an adaptive conformal inference method capable of efficiently handling deviations from exchangeability caused by random label noise. We validate our method through extensive numerical experiments demonstrating its effectiveness on synthetic and real data sets.
arXiv Detail & Related papers (2025-01-29T23:55:23Z)
Assessing the Viability of Synthetic Physical Copy Detection Patterns on Different Imaging Systems [4.156535226615695]
This paper explores the potential of synthetic physical Copy Detection Patterns (CDP) to improve the robustness of anti-counterfeiting systems. By leveraging synthetic physical CDP, we aim at enhancing security and cost-effectiveness across various real-world applications.
arXiv Detail & Related papers (2024-10-03T15:21:35Z)
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks [90.52808174102157]
In safety-critical applications such as medical imaging and autonomous driving, it is imperative to maintain both high adversarial robustness to protect against potential adversarial attacks. A notable knowledge gap remains concerning the uncertainty inherent in adversarially trained models. This study investigates the uncertainty of deep learning models by examining the performance of conformal prediction (CP) in the context of standard adversarial attacks.
arXiv Detail & Related papers (2024-05-14T18:05:19Z)
Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study [61.65123150513683]
multimodal foundation models, such as CLIP, produce state-of-the-art zero-shot results. It is reported that these models close the robustness gap by matching the performance of supervised models trained on ImageNet. We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark.
arXiv Detail & Related papers (2024-03-15T17:33:49Z)
f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization [9.591164070876689]
This paper presents a unified optimization framework for fair empirical risk based on f-divergence measures (f-FERM) In addition, our experiments demonstrate the superiority of fairness-accuracy tradeoffs offered by f-FERM for almost all batch sizes. Our extension is based on a distributionally robust optimization reformulation of f-FERM objective under $L_p$ norms as uncertainty sets.
arXiv Detail & Related papers (2023-12-06T03:14:16Z)
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance [53.45700148820669]
Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods.
arXiv Detail & Related papers (2023-03-23T02:55:50Z)
Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees [0.0]
Variational Markov Decision Processes (VAE-MDPs) are discrete latent space models that provide a reliable framework for distilling verifiable controllers from any RL policy. We introduce the Wasserstein auto-encoded MDP (WAE-MDP), a latent space model that fixes those issues by minimizing a penalized form of the optimal transport between the behaviors of the agent executing the original policy and the distilled policy. Our experiments show that, besides distilling policies up to 10 times faster, the latent model quality is indeed better in general.
arXiv Detail & Related papers (2023-03-22T13:41:42Z)
Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy [9.755020926517291]
We propose an evaluation methodology for synthetic data that avoids assumptions about the representativeness of proxy tasks. We measure the likelihood that published conclusions would change had the authors used synthetic data. We advocate for a new class of mechanisms that favor stronger utility guarantees and offer privacy protection.
arXiv Detail & Related papers (2022-08-26T14:57:21Z)
Differential privacy and robust statistics in high dimensions [49.50869296871643]
High-dimensional Propose-Test-Release (HPTR) builds upon three crucial components: the exponential mechanism, robust statistics, and the Propose-Test-Release mechanism. We show that HPTR nearly achieves the optimal sample complexity under several scenarios studied in the literature.
arXiv Detail & Related papers (2021-11-12T06:36:40Z)
Machine learning attack on copy detection patterns: are 1x1 patterns cloneable? [14.784426936848604]
We consider a copy attack against the copy detection patterns (CDP) based on machine learning. The experimental based on samples produced on two industrial printers demonstrate that simple detection metrics used in the CDP authentication cannot reliably distinguish the original CDP from their fakes.
arXiv Detail & Related papers (2021-10-05T17:06:28Z)
Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
arXiv Detail & Related papers (2020-11-24T19:52:38Z)
Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost Functions [80.12620331438052]
deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features. Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets. We argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance.
arXiv Detail & Related papers (2020-06-25T08:46:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.