cs.CR · 2026-10-14 · No. 143
Cryptography and Security, 2026-10-14.
10 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
10 entries-
01
Bytes to Threats: Byte-Sequence Transformer For Malware Detection
Abdelrahman Yassin Eljamal, Abdeltawab Hendawi
cs.CR · cs.AI
Existing malware detection approaches heavily rely on handcrafted features derived from static or dynamic analysis of the executable files. These methods require specialized domain expertise, dedicated analysis tools, and time-consuming analysis, which limits their scalability and robustness in the face of the increasing complexity and diversity of modern malware. Consequently, there is a growing interest in approaches that operate directly...
-
02
Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
Yang Luo, Tiantian Ji, Zifeng Kang, Yucheng Wang, Yong Liu, Zhiyi Yin, Xinran Liu
cs.CR · cs.AI
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution. However, this paradigm introduces a new security risk, which we term Jev Program Decision Hijacking (JPDH): attacker-controlled contexts can redirect program decisions through schema-valid Jev judgments. Existing evaluations focus primarily on model-level attacks or...
-
03
DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Chengtao Jian, Kai Yang
cs.CR · cs.AI · cs.CV
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal preference data remains largely unexplored. Existing preference poisoning attacks either corrupt explicit supervision signals or require visible triggers, making them detectable under human inspection. We introduce DPOison-VL, the first clean preference poisoning attack against VLM-DPO, which...
-
04
Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence
Tobias Hürten, Johannes F. Loevenich, Florian Spelter, Erik Adler, Laurin Holz, Maxime Schwarzer, Thies Moehlenhof,...
cs.CR · cs.LG
This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emulation, realistic user behaviour modelling for benign network traffic and adversarial profiles, and the generation of cybersecurity scenarios through open toolkits. By supporting live and deferred feature extraction at the packet and flow levels, the gym facilitates the creation of labelled synthetic datasets for training...
-
05
Towards Safe Autonomy for Computer Use
Dominik Seip, Bartol Markovinović, Matthias Hein
cs.CR · cs.LG
The safety of LLM-based agents currently rests on alignment training and safety classifiers, neither of which can rule out that a sophisticated indirect prompt injection (IPI) goes through and causes significant harm. Recent work therefore builds agents with information-flow guarantees that rely on structured tool interfaces to interact with the environment. Computer Use Agents (CUAs) act visually on the computer screen, which does not...
-
06
Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents
Kristoffer Hempel, Nils Loose, Lorenzo Cavallaro, Thomas Eisenbarth
cs.CR · cs.LG
Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an agent to act with the user's authority on any resource it can access. The reach that gives an agent its utility is equally available to an attacker who can steer it. Anything an agent ingests can carry an injected instruction, and since the model does not reliably distinguish instructions from...
-
07
FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation
Xi Chen, Chunyi Zhou, Rui Zeng, Xiaogang Xu, Zhe Liu, Shouling Ji
cs.CR · cs.AI
Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce targeted behaviors while maintaining normal performance on benign inputs. In this work, we make a key observation specific to federated LLM...
-
08
HULK: An Efficient Algorithm for Enabling Fast Bulk Bitwise Operations on Homomorphically Encrypted Data
Mayank Kabra, Phillip Widdowson, Harshita Gupta, Rakesh Nadig, Nisa Bostancı, Eirini Tzermpou, Rakesh Kumar, Spiros...
cs.CR · cs.AR · cs.DC
A wide range of important cloud applications, e.g., database analytics, graph analytics, and genome analysis, spend a considerable amount of time performing bulk bitwise operations (e.g., AND, OR, XOR). These applications often operate on highly sensitive data, making data privacy a critical concern. Homomorphic encryption (HE) enables secure computation on encrypted data without requiring decryption, ensuring privacy in untrusted and shared...
-
09
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu
cs.CR · cs.AI · cs.CL
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for agents to decode and follow. We evaluate Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success. In the primary setting with shortened skills, the variants achieve attack success rates of...
-
10
Holding Agents Accountable with Verifiable Agent Insurance
Cheng Hua, Taro Tsuchiya, Nicolas Christin, Giulia Fanti
cs.CR · cs.AI
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused on preventing such misbehavior, we consider how to recover after an agent misbehaves. We propose verifiable agent insurance (VAI), a framework for agent providers to commit financially to promises, a list of programmatically-specified policies that an agent is meant to follow. These promises...
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.