跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1959新增论文
+1550其中 AI 相关
+212已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-17 23:20 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 02:28 — 2026-11-18 02:28(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:2026-11-17 23:20最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 02:59

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。

25,786 已收录论文21,491 AI 相关7,725 有修订112 HF 社区发现

浏览论文库

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。部分信源异常,查看状态 →

找到 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 23:19(北京时间)
新论文 · v1arXiv:2611.12532

ML Models Are Not Ciphers: Power Analysis for Weight Extraction Is Harder Than You Think

Mohammed Qaiss, Peter Horvath, Michal Shagam, Lejla Batina, Zhuoran Liu, Eyal Ronen, Mahmood Sharif, Yuval Yarom

原文摘要

Can power-analysis techniques reveal secret weights of machine-learning models? Multiple recent works demonstrate proof-of-concept attacks that can partially recover such weights. To that end, these works build on techniques from cryptographic engineering, treating the model as a ``cipher'' and its secret weights as keys. We question the basic assumption behind such straightforward adaptations of cryptographic attacks and highlight the challenges arising when applying past techniques to fully recover all layers of deep neural networks. Unlike past works, which extract only a few weights, typically from shallow layers, we investigate the recovery of complete networks. Moreover, we target fully trained and functional models, rather than untrained, randomly initialized networks. To focus on fundamental challenges, we assume an unrealistically strong side-channel adversary that can directly observe the output of the leakage model without any added noise. With this adversary, we show that machine-learning models differ significantly from cryptographic implementations, giving rise to unique challenges that have not been observed in the prior art. We observe two main differences between machine-learning models and ciphers. First, in contrast to the high-diffusion nonlinear integer arithmetic prevalent in cryptographic schemes, machine-learning models tend to use limited-precision floating-point arithmetic and low-diffusion linear operations. We show that these operations introduce difficulties in weight recovery, often requiring an unexpectedly large number of traces, even under ideal channel conditions. Second, we observe that, unlike ciphers, which aim to increase the data entropy, machine-learning models aim to reduce it. This reduces data variability as the algorithm progresses, hampering weight recovery in deep layers of the model. (details can be found in the paper)

cs.CR

版本更新 · v2arXiv:2606.23496

TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization

Matan Ben-Tov, Mahmood Sharif

原文摘要

Discrete text-trigger optimization -- searching for text sequences that, when ingested by a model, steer it toward a specified objective -- underpins model red-teaming (e.g., LLM jailbreaks), as well as auditing and interpretability. However, the current state of discrete optimizers hinders their adoption and progress. First, existing optimizers, when open-sourced at all, are scattered across research codebases tied to specific models, objectives, and problem domains. Second, optimizers proliferate, each requiring engineering overhead to use or extend, and remaining hard to compare head-to-head. Together, these raise the bar for adopting optimizers in existing or new domains, and for advancing them via new strategies. We address these gaps with TROPT, the first open-source framework that unifies discrete optimizers' execution and standardizes their development under a single interface. TROPT makes it easy to customize end-to-end optimization recipes by swapping any component -- models, objectives, and optimizers -- extending its reach across domains and new applications. TROPT currently ships with 40+ optimization recipes -- covering applications such as jailbreaking and probing model internals -- built from 15+ optimizers (spanning white-box to black-box access) and 15+ losses, from foundational to state-of-the-art methods. Demonstrating its utility, we leverage TROPT in several studies: (i) controlled, large-scale experiments comparing and enhancing optimization strategies for LLM jailbreaks, revealing potent-yet-underadopted techniques; and (ii) porting optimizers across applications and domains (e.g., from LLM jailbreaks to corpus poisoning). In all, TROPT significantly lowers the barrier to adopting and advancing discrete text optimization.

cs.LG · cs.CR

新论文 · v1arXiv:2610.36665

Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models

Lior Ziv, Mahmood Sharif

原文摘要

While few-step distilled text-to-image models have gained traction due to their fast generation times, the speed-up implications on their unsafe generation rates remain unknown. We uncover an inherent tension between speed and safety: few-step models are often more unsafe than their teachers, and reducing the number of inference steps consistently raises unsafe generation rates. We further find that acceleration makes unsafe concepts harder to erase in few-step models, with existing concept-erasure methods markedly less effective than in teachers. We offer a mechanistic diagnosis for why erasure methods fail on few-step models, finding that the fragility of few-step models' generation process and the way generation guidance is usually distilled into those models may hinder established concept-erasure methods. To address the speed-safety trade-off, we propose DICE (Distillation-Integrated Concept Erasure), a post-distillation erasure method tailored for few-step models. DICE aligns both its latent construction and its generation-preservation loss with the distillation method that produced the model, keeping erasure faithful to few-step models. DICE demonstrates strong results in our evaluation. For example, on FLUX Schnell, DICE reduces unsafe-generation rate to 0.046 (vs. at least 0.161 for prior erasure methods we test), while mostly preserving benign generation quality.

cs.CV · cs.CR