Taejoong Chung

Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi et al.

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly available deepfake datasets. In this work, we study 8 state-of-the-art detectors and argue that they are far from being ready for deployment due to two recent developments. First, the emergence of lightweight methods to customize large generative models, can enable an attacker to create many customized generators (to create deepfakes), thereby substantially increasing the threat surface. We show that existing defenses fail to generalize well to such \emph{user-customized generative models} that are publicly available today. We discuss new machine learning approaches based on content-agnostic features, and ensemble modeling to improve generalization performance against user-customized models. Second, the emergence of \textit{vision foundation models} -- machine learning models trained on broad data that can be easily adapted to several downstream tasks -- can be misused by attackers to craft adversarial deepfakes that can evade existing defenses. We propose a simple adversarial attack that leverages existing foundation models to craft adversarial samples \textit{without adding any adversarial noise}, through careful semantic manipulation of the image content. We highlight the vulnerabilities of several defenses against our attack, and explore directions leveraging advanced foundation models and adversarial training to defend against this new threat.

Weitong Li, Yuze Li, Taejoong Chung

The Resource Public Key Infrastructure (RPKI) secures Internet routing by binding IP prefixes to authorized Autonomous Systems, yet its RSA foundations are vulnerable to quantum adversaries. A naive swap to post-quantum (PQ) signatures (eg Falcon) is a poor fit for RPKI's bulk model: every relying party (RP) repeatedly fetches and validates the entire global repository, so larger keys and signatures inflate bandwidth and CPU cost, especially during a long dual-stack transition. We present pqRPKI , a post-quantum RPKI framework that pairs a multi-layer Merkle Tree Ladder (MTL) with RPKI objects, customized to relocate per-object verification material from certificates into the Manifest. To update RPKI for Merkle tree based schemes, pqRPKI redesign the RPKI manifest and delegation chain, introduces a ladder-guided sync and bulk-verification workflow that lets validators localize diffs top-down and rebuild trees bottom-up. pqRPKI also preserves current RPKI objects and encodings, supports both hosted and delegated operation, and provides an additive migration path that coexists with today's trust anchors for dual-stack deployment with little size overhead. Implemented as a working publication point (PP) and RPs, we show that pqRPKI reduces repository footprint to 546.8 MB on average (65.5%/83.1% smaller than Falcon/ML-DSA), cuts full-cycle validation to 102.7 s, and achieves 118.3 s end-to-end PP to Router time, enabling sub-2-minute operating cadences with full-repository validation each cycle. Dual-stack deployment with RSA only adds just 3.4% size overhead versus today's RPKI repositories.