Jason

This paper designs and validates a Quantum Key Distribution (QKD) based mechanism to secure non-3GPP access in 5G networks, demonstrating that it achieves Information-Theoretic Security while improving key establishment speed compared to traditional methods.

The paper proposes a three-step differentially private pipeline to simulate disease spread on sensitive contact networks, demonstrating that the added noise for privacy is generally small relative to other sources of error.

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are distinct from inherent LLM flaws.

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

The paper proposes WARDEN, a distributionally robust adversarial training framework that significantly reduces LLM vulnerability to adversarial attacks by dynamically reweighting hard adversarial examples within a divergence ball.

The paper introduces BLADEI, a hardware-accelerated framework that screens FPGA configuration bitstreams for anomalies in real-time, overcoming the latency bottleneck of traditional software-based detection.

This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing both attack scenarios and a robust mitigation solution.

The paper argues that current LLM benchmark datasets are often contaminated by being included in pretraining data, and proposes that future benchmarks must be contamination-resistant and support inference to maintain reliable model evaluation.

HammerSim is a novel gem5-based framework that provides full-system visibility to model the RowHammer vulnerability, allowing researchers to evaluate complex hardware and software mitigations.

HammerSim is a new gem5-based framework that provides full-system visibility to model the RowHammer vulnerability, allowing researchers to study complex OS effects and hardware/software mitigations.

The paper introduces Agora, a domain-aware multi-agent framework that successfully detects deep, previously unknown logic bugs in complex consensus protocols, outperforming existing LLM-based analysis methods.

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.

The paper introduces TECCI, a novel and challenging benchmark dataset of 7550 image-edit pairs, and demonstrates that current state-of-the-art text-guided image editing models struggle significantly with complex instructions, particularly those involving spatial reasoning and creative edits.

The paper introduces TravelEval, a comprehensive, six-dimensional benchmarking framework that evaluates LLM-powered travel plans using realistic spatio-temporal simulation, revealing that current LLMs struggle with globally-optimized, multi-dimensional planning.

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achieving competitive performance and throughput gains.

This paper introduces and analyzes a consistent estimator for the sub-Gaussian parameter ($\xi_*^2$), providing convergence rates and demonstrating its applicability in large-scale biological enrichment studies.

This paper presents a data-driven method to estimate external joint torques without dedicated force sensors, enabling force-feedback teleoperation on low-cost arms.

This paper proposes a post-training framework called Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT) to teach language models to reason by analogy.