跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

采集已暂停
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+0新增 AI 导读

arXiv 最近完成扫描：等待完成 · 全站最近入库：2026-11-02 00:39各信源进度 →

统计口径与数据新鲜度

统计 2026-11-03 20:27 — 2026-11-04 20:27（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：尚未完成最近发现新增版本：2026-11-02 00:39库内论文最新更新时间：2026-10-30 01:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

8,677 已收录论文7,675 AI 相关1,866 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。

找到 2 篇论文 · 按版本更新时间排序等待首次采集
新论文 · v1arXiv:2610.38799

CARI: Cross-Boundary Adversarial Runtime Injection in Coding-Agent Workflows

Jie Fu, Shuang Wu, Ashish Kundu, Wendy Hui Wang, Yuan Hong

Coding agents increasingly develop, test, and integrate software whose components are owned by different developers, teams, or services. This exposes a distinct attack surface: a malicious or compromised peer development role can manipulate a live component of the software under development (e.g., a backend service, test harness, CI job, or deployment service) and influence the runtime feedback that another role's coding agent must process to complete its task. Although such a component has legitimate diagnostic authority to report its own state, it has no action authority over the victim's local files, credentials, shell, or development environment. We introduce Cross-Boundary Adversarial Runtime Injection (CARI), a direct runtime-feedback injection setting that exploits this authority mismatch. Rather than explicitly compromising the victim's prompt, model, tools, or local environment, the attacker covertly embeds malicious instructions in task-relevant runtime feedback produced by a peer-controlled development component. The victim then interprets that feedback as part of normal debugging or recovery, and may translate the diagnostic guidance into unauthorized victim-side actions. We instantiate ten different attacks based on CARI, spanning resource exhaustion, information exposure, and development-state manipulation. Across four programming languages and five code-capable models, CARI succeeds in 2,845/3,000 (94.8%) trials. Furthermore, CARI transfers effectively to product-level coding agents, achieving 61.3% attack success on Codex and 58.7% on Claude Code. By contrast, prompt-level defenses exhibit a security-utility trade-off: generic warnings are ineffective, whereas explicit policies suppress attacks but substantially over-refuse legitimate actions.

尚无 AI 解读，展示原文摘要

cs.CR · cs.SE
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37488

Revisiting Privacy Risks in Quantized Deep Neural Networks

Jie Fu, Ren Li, Wendy Hui Wang

Model quantization has become a fundamental technique for enabling the efficient deployment of large-scale deep neural networks (DNNs) in data-intensive applications by reducing model size. Despite its widespread adoption, the impact of quantization on training data privacy --- particularly vulnerability to membership inference attacks (MIAs) --- remains largely unexplored. In this paper, we present the first comprehensive empirical study of privacy risks in quantized DNNs, evaluating eight state-of-the-art MIA attacks across six representative quantization methods. Our results reveal that practical quantization levels (4-8 bits) have limited impact on membership privacy risks, with quantized models remaining largely as vulnerable as their full-precision counterparts. Although aggressive low-bit quantization (e.g., 2-bit) can provide meaningful privacy gains, these benefits come at the cost of substantial utility degradation. To understand the underlying causes of these observations, we systematically analyze how different quantization strategies affect model behaviors and outputs, and how these changes influence privacy vulnerability. Beyond evaluating attack risks, we further investigate whether existing privacy defenses developed for full-precision DNNs can effectively protect QNNs. Our results show that these defenses provide only limited additional privacy protection when applied to quantized models, while further amplifying utility degradation. Our study provides practical guidance for privacy-aware deployment of quantized DNNs and motivates the development of new attack and defense mechanisms for QNNs. Our code and datasets are publicly available at https://github.com/JeffffffFu/Priv-QDNN.

尚无 AI 解读，展示原文摘要

cs.CR
arXiv ↗PDF ↗