Han Hu

The paper introduces ReproMIA, a novel and efficient framework that uses model reprogramming to proactively amplify and detect latent privacy leakage for Membership Inference Attacks (MIAs), significantly outperforming state-of-the-art methods, especially in low False Positive Rate regimes.

This paper analyzes the potential downsides of integrating advanced AI and smart capabilities across the Edge-Cloud continuum in modern industry, focusing specifically on security vulnerabilities, side effects, and cyber threats.

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to unnecessary data disclosure.

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outperforming existing state-of-the-art methods.

This survey proposes a proactive, lifecycle-based framework, utilizing the C5 Interaction Model, to detect emerging adversarial synthetic narratives generated by Generative AI, moving beyond traditional reactive detection.

The paper proposes Energy-Aware NECO, a single-pass hybrid detector that combines geometric ratio and logit-based energy scores to achieve superior pixel-wise out-of-distribution detection for semantic segmentation on edge devices.

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly improving agent performance across multiple mobile benchmarks.

This survey proposes a proactive, lifecycle-based framework, utilizing the C5 Interaction Model, to detect emerging adversarial synthetic narratives generated by GenAI, moving beyond traditional reactive detection.

The paper introduces DEBENCH, a novel framework that evaluates binary decompilers based on three orthogonal dimensions—readability, recompilability, and functionality—revealing that functional recovery is significantly harder than simple code readability.

The paper introduces SCALR, a novel framework that generates synthetic user-item interaction data from a source domain to augment a target recommendation domain, significantly improving system performance in A/B tests.

The paper demonstrates that specialized coding agents, using only text and image access within a sandbox, can effectively solve complex omnimodal tasks, often outperforming state-of-the-art native omnimodal models.