Aegis is a client‑side defense for medical federated learning that protects against model inversion attacks by adding a masking gradient derived from locally synthesized data. The method exploits the fact that attacks fail when the effective batch size exceeds the model’s leakage capacity, turning this bottleneck into a privacy guarantee. Experiments on MNIST, CIFAR‑10, and MedMNIST datasets show that Aegis neutralizes state‑of‑the‑art attacks while preserving model accuracy and adding only modest overhead.
By Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou
The paper introduces an explainable pedestrian routing method that estimates perceived safety by first generating a natural‑language caption from street‑level images and then deriving risk scores solely from structured features of that caption. Benchmarking nine captioning setups against a CLIP image‑embedding baseline shows comparable performance, and the system was deployed on over 650,000 images across 36 wards in Manchester and Huddersfield. Field validation with 3,669 ratings from 70 participants revealed a modest but statistically significant correlation (r = 0.262) with human judgments, while a stronger supervised benchmark did not translate into better real‑world performance.
By Simon Parkinson, Paloma Liu, Wei Zheng, Mohammadreza Sheikhfathollahi
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
By Ali Aouad, Aymane El Gadarri, Vivek F. Farias
DAMPER is a new technique for actor‑critic methods that reduces action oscillation in continuous control tasks. It combines the native actor gradient with a temporal‑consistency gradient using conflict‑conditioned projection and adaptive magnitude control, ensuring the auxiliary component aligns positively with the actor gradient. Experiments on TD3 and SAC across six tasks show that DAMPER consistently lowers oscillation compared to baseline agents and outperforms other methods in most task‑backbone pairs.
By Seokmin Ko, Taewon Goo, Kihyuk Hong
RAGScope is a leakage‑controlled, cost‑aware protocol that evaluates evidence‑gating mechanisms for retrieval‑augmented generation (RAG) systems using only the task input, retrieved context, and answer text. The enhanced gate, RAGScope‑E, achieves an AUROC of 0.798 and an average precision of 0.660 on three RAGTruth tasks, outperforming ROUGE‑L by 0.034 in pooled AP and delivering 0.748 precision within a top‑10% review budget. It operates quickly (6.22 ms per example on CPU) and demonstrates that cheap evidence gates can effectively triage RAG outputs, though calibration must be validated and adapted for each target domain.
By Zeming Liu, Qibai Chen, Jingtao Zhang, Hang Lyu
The paper introduces HealBench, a benchmark of 265 runtime errors from 18 real-world repositories, and HealGuard, a safety framework that restricts healing code to an analyzable subset of Python and applies static and dynamic taint analysis. Using these tools, the authors evaluate a dedicated healing method and three general coding agents powered by different LLM backbones, achieving a 38.11% resume rate and a 28.68% test‑pass rate, while HealGuard flags 17.4% of successful healings as potentially unsafe. The study demonstrates that current LLM agents can meaningfully repair real repository crashes, but also highlights significant safety concerns that the Guardrail framework can detect, albeit with a high false‑positive rate.
By Gou Tan, Pengfei Chen, Zhensu Sun, Jieke Shi, Junkai Chen, Ting Zhang, Weifeng Sun, Junda He, Shuai Liang, Chuanfu Zhang, Lwin Khin Shar, David Lo
The paper introduces FDCU, a dual‑constrained subspace projection framework designed to improve machine unlearning for large language models. FDCU limits parameter updates with a dual‑masking rule that preserves general knowledge via Fisher Information while preventing the activation of spurious suppressors through the Principle of Minimal Functional Intervention. Experiments show that FDCU achieves state‑of‑the‑art robustness against retraining attacks while maintaining near‑lossless general utility, thereby ensuring durable safety for LLMs.
By Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang
The paper introduces FailBank, a four‑stage self‑evolving framework that transforms runtime feedback from safety shields into lasting policy improvements for vision‑language‑action (VLA) models. By using a counterfactual correction teacher, outcome‑aware admission, and guarded LoRA updates, FailBank converts useful shield proposals into corrective targets while preserving successful actions as anchors. Experiments on the VLA‑Arena benchmark show that FailBank boosts task success rates by up to 8.5 percentage points and reduces cumulative policy cost by up to 35.6%, outperforming both base policies and traditional runtime shielding.
By Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang, Meng Jiang
PhantomEnvironments is a framework that trains large language model agents in synthetic, rule‑generated fictional worlds. By creating multi‑turn reinforcement learning environments where agents search templated articles to answer multi‑hop questions, the approach eliminates the need for costly human data or hallucinated LLM‑generated settings. Agents trained in these zero‑cost, purely rule‑based worlds transfer effectively to real‑world multi‑hop search benchmarks, often surpassing models trained on real data, and demonstrate scalable search behavior that grows linearly with question difficulty.
By Anmol Kabra, Swathi Saravana Selvam, Albert Gong, Chao Wan, Christian Belardi, Dongyoung Go, Katie Z. Luo, Kilian Q. Weinberger
arXiv:2609.40322v1 Announce Type: cross
Abstract: Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented lang...
By Anson Y. Lam, Shuqing Li, Michael R. Lyu
arXiv:2605.27981v2 Announce Type: replace
Abstract: Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases...
By Soohan Lim, Joonghyuk Hahn, Hyundong Jin, Yo-Sub Han
arXiv:2609.34211v2 Announce Type: replace
Abstract: In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud reasoning. However,...
By Linbo Shao, Huilin He, Yating Lou, Dawei Cheng
arXiv:2609.37054v2 Announce Type: replace
Abstract: Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to...
By Xianhui Zhang, Jian Yu, Chengyu Xie, Chenhang Cui, Shuyi Miao, Pengyang Shao, Yu Zheng, Fei Shen, Tat-Seng Chua
arXiv:2603.10210v2 Announce Type: replace-cross
Abstract: While Diffusion Models excel in text-to-image synthesis, they frequently suffer from catastrophic concept omission when generating complex mu...
By Zitong Wang, Zijun Shen, Haohao Xu, Zhengjie Luo, Weibin Wu
arXiv:2609.35596v2 Announce Type: replace-cross
Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their con...
By Saswat Das, Parvati Viswanathan, Daniel Donnelly, Chang Huang, Sahar Abdelnabi, Ferdinando Fioretto
arXiv:2609.38205v1 Announce Type: new
Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the tran...
By Muhammad Usama, Dong Eui Chang
arXiv:2609.38976v1 Announce Type: new
Abstract: Demographic fairness gaps in automatic speech recognition are almost always reported from a single training run. We fine-tune the Q-former projector an...
By Srishti Ginjala, Eric Fosler-Lussier, Srinivasan Parthasarathy
arXiv:2609.38291v1 Announce Type: cross
Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtim...
By Zhuo Liu, Moxin Li, Zhixin Ma, Wentao Shi, Wenjie Wang, Fuli Feng
arXiv:2609.38371v1 Announce Type: cross
Abstract: Existing LLM-driven robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focu...
By Guangxin Zhao, Yiran Hu, Yuan Cao, Chenxi Jiang, Jianfei Yang, Yegang Du, Yasuyuki Taki, Yoshifumi Kitamura, Lin Gu, Zhi Zheng
arXiv:2609.38389v1 Announce Type: cross
Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...
By Yelyzaveta (Lisa), Husieva, Lauren Alvarez