The paper introduces PASS, a Provenanced Access Subaccount System that replaces traditional key-based control with verifiable provenance-based control for blockchain wallets, enabling secure, multi-ac…

This paper proposes CoHarden, a co-generation framework for automated program repair that uses a lax signal as an in-loop convergence criterion to prevent lax regressions.

This paper constructs and proves the security of 3-pass Authenticated Key Exchange (AKE) protocols for both KA-based and KEM-based primitives within the commitment-based model, improving upon previous…

The paper introduces Acceptance Cards, a rigorous four-diagnostic standard, to provide a comprehensive and reliable evaluation protocol for claims of safe fine-tuning defenses.

This study comparatively assessed the usability of passkeys versus passwords for Wi-Fi captive portal authentication, finding that while passkeys were perceived as more usable, captive portal limitati…

The paper demonstrates that while distilling large language models for medical QA can significantly improve final answer accuracy, this gain often comes at the cost of factual accuracy and detailed re…

This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.

The paper introduces PassNet, a large-scale ecosystem for generating compiler passes using LLMs, demonstrating that LLMs can significantly accelerate graph compilation for long-tail workloads, suggest…

The paper shows that safety failures in low-resource languages are due to a failure in the model's safety decision calibration, not a lack of underlying knowledge, and proposes a recalibration method…

This paper reports experiences and takeaways from using puzzles to teach critical testing literacy (CTL) through workshops, introducing the pedagogical framework P4TEST.

PaCo-VLA introduces a passivity-shielded compliance prior to safely bridge the gap between high-level Vision-Language-Action (VLA) semantic outputs and low-level, force-sensitive robotic control.

Permit is a novel framework that enforces fine-grained, permission-aware control over the hidden states of LLMs, preventing information leakage even when sensitive data is present in the context.

The paper proposes a novel, customizable 'Pick and Sort' graphical authentication scheme where users select and arrange visual elements in a grid, demonstrating its feasibility for non-time-critical a…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

The paper introduces AMNESIA, the first large-scale, open-source benchmark for medical unlearning, demonstrating that current unlearning methods struggle to separate individual patient data from share…

The paper identifies and measures a critical failure mode where LLM agents violate policies by losing or corrupting directive-bearing state during the process of assembling the decision context, and p…

The paper introduces Relay On-Policy Distillation (Relay-OPD), a method for on-policy distillation that constructs relay trajectories to address prefix failure and improve performance.

The paper argues that over-engineered university cybersecurity protocols, while necessary, create significant accessibility barriers that disproportionately harm remote international students, particu…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper investigates how digital devices in U.S. prisons create privacy and security risks for incarcerated users, finding that pervasive surveillance and arbitrary policies negatively impact their…