cs.CR · 2026-08-31 · No. 101
Cryptography and Security, 2026-08-31.
11 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
11 entries-
01
Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
Pietro Tiberi, Gabriele Marcelli, Vitangelo Lasorella
cs.CR · cs.DC
Central Bank Digital Currency (CBDC) interbank settlement systems operating on Distributed Ledger Technology (DLT) face a fundamental trade-off: blockchain transparency enables trustless verification but exposes commercially sensitive bilateral transaction flows to all network participants. We propose a confidential interbank settlement protocol for permissioned Ethereum-compatible networks that resolves this tension through a relaxed sender...
-
02
LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
Jingjing Nie, Jiawei Guo, Krishna Meda, Haipeng Cai
cs.CR · cs.AI
Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model (LLM)-based agents, which can plan, use tools, retain state, and revise actions across multi-step workflows, are being rapidly adopted to automate this work. Given the consequences of delegating security decisions to autonomous systems,...
-
03
LongPIBench: A Long-Context Benchmark for Prompt Injection
Yupei Liu, Yuqi Jia, Neil Zhenqiang Gong, Jinyuan Jia
cs.CR · cs.AI
Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context benchmark...
-
04
Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers
Owen Cox, April Xu, Weiyu Xu
cs.CR · cs.AI · cs.GT · eess.SP · stat.AP · stat.ME
In applications, it is often required to test objects or people to determine their qualities in terms of certain metrics. However, besides being naturally noisy, the test results can be corrupted by adversarial behaviors of objects or people being tested (test takers). For example, dishonest test takers can cheat in the exams to distort the test results. With the development of AI technologies, such distortions driven by cheating using AI...
-
05
Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers
Abrar Alotaibi, Muhammad Shahid Jabbar, Sadam Al-Azani, Moataz Ahmed
cs.CR · cs.AI · cs.CL
Practitioners defend large language models (LLMs) by stacking defenses, assuming the layers compound. A stack is an ensemble, and ensembles compound only under a condition the LLM security literature recommends but never measures: the members must fail on different inputs. Two instruments make that measurable. The Adversary Access-Tier Model (AATM) grades an adversary by the access it holds, from system-only (A0) to influence over training...
-
06
Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code
Animesh Shaw
cs.CR · cs.AI · cs.MA · cs.SE
Large language models are increasingly used to author Infrastructure-as-Code (IaC), where a single insecure default can be deployed directly into production. Prior evaluations report raw vulnerability counts for model-generated IaC, but without a human baseline they cannot determine whether models are actually worse than engineers. We introduce GenIaC-SecBench, a benchmark of 100 deployment scenarios stratified by architectural complexity,...
-
07
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Zi Liang, Xiaoyu Xu, Yanyun Wang, Minxin Du, Qingqing Ye, Haibo Hu
cs.CR · cs.AI
Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known injection attacks, deploying them in LLM agent environments remains challenging due to attack variants and emerging threats. Moreover, existing...
-
08
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification
Cameron Wilding, Mina Shaker, Fatemeh Ganji
cs.CR · cs.AI · cs.LG
Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment. Our framework explores complementary probe...
-
09
FISGuard: Defending Against Membership Inference via Fixed Input Subspaces
Haocheng Jiang, Hua Shen
cs.CR · cs.AI · cs.DC
As large language models are increasingly adopted in federated learning, protecting user privacy while performing parameter-efficient fine-tuning on distributed private data has become an important challenge. Although clients only share gradients instead of directly uploading raw data, the shared gradients may still leak membership information about training samples. ProjRes (S&P, 2026) further increases this risk: with less information and...
-
10
ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools
Yuqi Jia, Ruiqi Wang, Patrick Li, Yuepeng Hu, Peinian Li, Neil Gong
cs.CR · cs.AI
Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be carried out via malicious tools and typically require three conditions: (1) the agent selects the malicious tool for task execution, (2) the agent passes its runtime context as input arguments to the tool, and (3) the tool's implementation transmits these inputs to...
-
11
Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots
Xujun Che, Depeng Xu, Shuhan Yuan
cs.CR · cs.CL · cs.LG
Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that carry the practical weight, counterfactual memorization and adaptive extraction, and show that they do not control each other. Under $f$-DP, every adaptive extraction protocol with list budget $m$...
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.