cs.CR · 2026-06-16 · No. 25
Cryptography and Security, 2026-06-16.
4 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity
Ziniu Liu, Aiping Li
cs.CR · cs.IT · cs.LG
When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP guarantee for the joint output. This worst-case bound, however, does not answer the concrete inference question: at what k can an adversary actually identify a target person? This paper develops the information-theoretic framework needed to answer that question. We...
-
02
Automated jailbreak attack targeting multiple defense strategies
Qi Wang, Chengcheng Wan, Weijia He, Yanqing Li, Hanqi Sun, Xiaodong Gu, Jiangtao Wang
cs.CR · cs.AI
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their safety remains a critical concern due to their susceptibility to adversarial prompt-based attacks. In this paper, we present UNIATTACK, an adversarial testing framework designed from a defense-oriented perspective to systematically construct effective black-box attack prompts. Unlike prior approaches that rely on static...
-
03
FEnc$^2$: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding
Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen
cs.CR · cs.LG
Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead. These costs come not only from expensive low-level primitives, including Number Theoretic Transform (NTT), rotation, and key-switching, but also from inefficient ciphertext packing at the application level. Existing packing strategies typically preserve either neighboring data elements or feature grouping, but...
-
04
The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
Sipeng Xie, Qianhong Wu, Hengrun Lu, Ziliang Sun, Qi Wu, Bo Qin, Qin Wang
cs.CR · cs.AI · cs.ET · cs.MA
Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and opens a separate upstream session, so it holds the full interaction in plaintext. This makes the router an application-layer man-in-the-middle: it can rewrite agent tool calls, swap dependencies for typosquatted packages, trigger attacks only under audit-evading conditions, and passively exfiltrate...
This edition is part of The Daily Abstract — cs.CR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.