Nov 2026· Proceedings of the 2nd ACM Workshop on Deepfake, Deception, and Disinformation Security· 0 citations· 8 references
Misinformation and Its ImpactsDigital Media Forensic Detection
Abstract
Generative Artificial Intelligence (AI) has democratised content creation while scaling systemic threats in Deepfakes, Deception, and Disinformation (D3). As traditional content detection and watermarking are increasingly bypassed, this paper presents a position and baseline synthesis of Reverse Prompt Engineering (RPE) as a defensive capability. RPE inverts the generative pipeline to infer plausible instruction prompts and support, rather than definitively proving source-model attribution. Grounded in threat telemetry, we synthesise representative RPE frameworks while explicitly delineating the evidentiary limits of prompt recovery, attribution, and content provenance. We further evaluate RPE across public information, legal, and policy/governance viewpoints, analyse key technical limitations such as cross-modal generalisation, and outline a research roadmap to establish RPE as a cornerstone of digital provenance and AI accountability.
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9
This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27, and examines detection, segmentation, depth, classification, pose, oriented detection, tracking, export, quantization, and deplo...
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
