cs.AI · cs.CL · cs.LG · cs.CV · cs.CR · cs.SE · stat.ML · q-fin.TR · q-fin.ST · econ.GN · q-bio.QM · physics.soc-ph · math.OC · cs.RO · cs.HC
Josiah Dykstra · 2026-10-19
Attackers profit from what defenders do not understand. Software security has treated the gap between system behavior and human comprehension as a condition to narrow through analysis and assurance, booking the remainder as accepted risk. Agentic AI systems change that gap: when …
Nardine Basta, Robin Carpentier, Benjamin Zi Hao Zhao, Dali Kaafar · 2026-10-19
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which automated agents engage scammers to deplete their operational capacity, offers a…
Wan Ki Wong, Michele Ciampi, Rik Sarkar · 2026-10-19
Bitcoin-style Proof-of-Work (PoW) secures permissionless blockchains but spends substantial computation on hash puzzles which have no utility other than extending the chain. At the same time, we have seen that the rise of generative AI has created significant demand for computati…
Hao Chen, Junnan Xu · 2026-10-19
Invisible watermarks are used to mark who owns a painting. We show that a simple attack removes the most robust one we test. The attack redraws the watermarked painting with brush strokes, using a pretrained stroke-based renderer. We call this attack BrushOff. It needs no trainin…
Ramamonjy Andriamifidisoa, Rufine Marius Lalasoa · 2026-10-19
We revisit DM-RSA, an RSA variant that uses two independent moduli, whose original version was broken by Håstad's attack and contained an incorrect compromise-tolerance claim. We give a formal treatment of its repaired variant, DM-RSA-OAEP: (i) a complete IND-CCA2 security proof …
Rohan Menon, Chih-Hong Cheng · 2026-10-19
Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to the victim model. Yet each additional call gives the deployed system another opportunity to detect the attack and intervene. We introduce $\mathrm{ASR}_{\mathrm{S…
Ashok Subbabhatta Gopalakrishna · 2026-10-19
AI agents in containers act by opening network connections, and the text that drives them can be hostile. Controls placed between the agent and its tools are bypassed by a child process or a direct socket, and their approval is not tied to the connection the kernel later opens. W…
Nam Hoang Thanh, Trung Pham Duy, Lam Bui Thu · 2026-10-19
Machine-learning (ML) malware detectors are known to be vulnerable to adversarial samples. Generative adversarial networks (GANs) such as MalGAN, Mal-LSGAN, and our previous Mal-D2GAN can craft adversarial malware to probe and harden these detectors, yet they operate directly on …
Nicolas Ruiz · 2026-10-19
This paper derives an exact attenuation formula for multivariate cross-moments under differential privacy achieved through randomized response. From a proposed alternative formulation of randomization matrices compliant with differential privacy guarantees we show that, under att…
Ganxuan Yang, Siqi Wen, Shuyan Yu, Jidong Yuan · 2026-10-19
Hidden randomized rounding couples the privacy loss of successive integer releases. We study a rational-feedback mechanism under predictable signed-unit participation and full observation of every physical output. A preparation's lifetime connects three results. First, preserving…
Mengxiao Wang, Nitesh Saxena · 2026-10-19
Large language model (LLM) agents now trade real capital using news as evidence, yet they cannot reliably tell fabricated headlines from real news. Because they read the same feeds under near-identical policies, a single fabricated post can push them into the same trade at the sa…
Ahmed F. K. Koysha, Ferdi Sönmez · 2026-10-19
This study presents a 96-day longitudinal analysis of Secure Reliable Transport (SRT) protocol behavior in a production streaming environment between Iraq and Turkey, examining 262,672 transport metric samples and 5,033,104 system resource measurements collected between October 2…
Anastasiia Kucherenko, Melissa Chase, Esha Ghosh · 2026-10-19
Transparency systems -- such as Key Transparency (KT), Certificate Transparency, and binary transparency -- require that all honest participants see the same view of an untrusted server's directory, or, failing that, that the misbehaviour is publicly detected. Every existing desi…
Walid El Maouaki, Mohammad Izen, Nouhaila Innan, Alberto Marchisio, Muhammad Shafique · 2026-10-19
Quantum machine-learning (QML) models are increasingly considered for security applications, yet their adversarial robustness in malware analysis remains insufficiently understood. This paper presents Q-MALDetect, a hybrid convolutional and variational-quantum detector for byte-i…
Jieshuai Yang, Zhi Wang, Yan Jia, Zhenhua Wu, Jianfei Tang and others · 2026-10-19
Antivirus (AV) signatures encode valuable detection knowledge accumulated through expert analysis, yet repeated black-box queries can expose this knowledge for unauthorized reuse and targeted evasion. We propose Signature Knowledge Shielding (SKS), a design paradigm that protects…
Binbin Zhang, Yifeng Zhang, Xiaomeng Chen, Dongyao Chen · 2026-10-19
Tactile perception is crucial for precise robotic manipulation, providing an important foundation for dexterous, closed-loop force control. Among various tactile sensing techniques, magnetic tactile sensors stand out thanks to their fine-grained, three-dimensional force perceptio…
Xiaoyuan Bao, Jingsi Jiang, Jiao Shan, Yulong Cao, Haoyu Wang and others · 2026-10-19
Autonomous clinical-modeling agents can optimize predictive performance while violating conditions that make a model usable. We introduce LeakBench, an executable, guideline-derived audit suite that tests agent decisions for prediction-time leakage, calibration, site-level evalua…
Basile Schlosser, Jérémy Thibault, Catalin Hritcu · 2026-10-19
The security guarantees of existing formally verified compilers for compartmentalized programs in unsafe languages like C stop at a rather high level, assuming a built-in protection mechanism and a block-based memory model. Verifying a concrete, low-level enforcement mechanism fo…
Yinxiang Wang, Zehua Ma, Kejiang Chen, Weiming Zhang, Han Fang · 2026-10-19
LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the guardrail model becomes smaller or weaker, detection degrades substantially. This raises a natural question: can we retain strong IPI defe…
Mirza Masfiqur Rahman, MD Ajwad Akil, Imtiaz Karim, Ashish Kundu, Ramana Kompella and others · 2026-10-19
Code generated by large language models often passes every functional test while remaining insecure. These security hallucinations are common, written with high confidence, and repeated across samples, so neither the generator's own uncertainty nor static analyzers reliably catch…
Jin Han, Mingfeng Xin, Feng Liang, Jingtao Yu · 2026-10-19
Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its actions are finite and decisions recur. We present NIOCIS, a routing layer that folds execution logs into a loop-collapsed action graph (forward transitions plus r…
Ziyi Zhang, Ziyao Wang, Guoheng Sun, Ang Li, Jian Li · 2026-10-19
Hosted LLM services increasingly expose model identity as a product claim, but external users and auditors often cannot inspect which model configuration served a request. We study an auditor-assisted regime in which a trusted auditor enrolls claimed identities and prepares verif…
Yuchen Chen, Wei Cheng, Yuan Xiao, Junda He, Jieke Shi and others · 2026-10-19
Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external knowledge bases also introduces new attack surfaces. Existing data extraction attacks against RAG systems rely on either prompt injection…
Tue Le, Anh Nguyen Hoang, Gabriel Sasseville, Doseok Jang, Pierre-Luc Bacon and others · 2026-10-19
As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure code generation requires a signal whose reported progress remains aligned with actual program behavior under optimization; otherwise, an opt…
Zhicheng Fang, Han Sun, Jiachen Lei, Xinyi Fang, Zongmin Zhang and others · 2026-10-19
As jailbreak attacks against large language models (LLMs) become increasingly diverse, red-teaming has come to rely on large libraries of jailbreak prompts and attack strategies to evaluate the robustness of victim models and their defense settings. However, attack effectiveness …
Rahul, Manjesh Kumar Hanawal, Sameer G. Kulkarni, Tirumaleswar Reddy K · 2026-10-19
The threat of quantum computers breaking classical cryptographic is accelerating the adoption of quantum- resistant cryptographic algorithms. Several government agencies have set a tight time-line for upgradation of all system to support post quantum cryptographs. We study post-q…
Cheng Jin, Zhongtian Ma, Xiao Wang, Han Qi, Xiaoyu Wen and others · 2026-10-19
Large language models acquire broad knowledge from web-scale corpora during pretraining, including knowledge that could be hazardous if misused. Removing such knowledge from the model itself without degrading general capability is desirable but difficult, as it is deeply entangle…
Yibo Meng, Bingyi Liu, Lionel Z. Wang, Zhuoran Lu · 2026-10-19
Terminally ill patients generate extensive digital health data through hospital portals, physiological monitoring devices, consumer health applications, and end-of-life care platforms. Yet their ability to control this data is systematically undermined by the structural condition…
Jinbao Zhu, Kai Wan, Giuseppe Caire · 2026-10-19
Secure aggregation enables a server to compute the sum of users' gradients or model updates without revealing individual values. With user dropouts, correlated random keys protect local gradients while allowing recovery of the desired gradient sum. We consider three phases: key d…
Ajay Kumar Shrestha, Sandhya Joshi · 2026-10-19
Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed (non-IID) data because honest local updates may temporarily reduce performance on a…
Haoran Xue, Nikta Akbarpour, Gias Uddin, Song Wang · 2026-10-19
Large language model (LLM) coding agents, such as Claude Code, are increasingly used for security auditing, with task-specific skills providing reusable vulnerability-analysis procedures. However, their effectiveness in detecting real vulnerabilities and the reasons for their fai…
Tetsuya Sato · 2026-10-19
Differential privacy (DP) is a gold-standard definition of privacy designed to evaluate the privacy guarantee of databases. Rényi differential privacy (RDP) is an important variant of DP that gives tight evaluations of machine learning algorithms. These formulations are easy to u…
Nicholas Potteiger, Ankita Samaddar, Xenofon Koutsoukos · 2026-10-18
Autonomous cyber-defense agents trained using reinforcement learning (RL) are increasingly adopted for defending enterprise computer networks. However, existing approaches may become brittle as attacker capabilities evolve and enable new attack strategies. In this work, we study …
Giacomo Longo, Alessandro Cantelli-Forti, Alessio Merlo, Enrico Russo · 2026-10-18
Modern maritime navigation depends on mandatory wireless inputs, most notably GNSS and AIS, whose reception can be spoofed or jammed. When groundings or collisions occur, liability and safety investigations often turn on whether RF interference corrupted bridge instruments, yet t…
Nanjun Zhou, Yiming Li, Yukun Chen, Ting Qiao, Enhao Huang and others · 2026-10-18
Tool poisoning has emerged as a critical security threat to LLM agents, where adversaries embed malicious instructions in tool descriptions or external resources that enter the agent's context, allowing adversaries to manipulate agent's tool selection process. However, existing t…
Lilia-Eliana Popescu-Apreutesei, Sabina-Cristiana Necula · 2026-10-18
Comparing the predictive performance and computational cost of flow-based intrusion detection experiments requires both quantities to be available for each run. GreenNIDS connects benchmark execution on public NetFlow datasets to a reusable analysis dataset. Model implementations…
Youlong Ding · 2026-10-18
We revisit the proof-of-useful-work (PoUW) scheme in Pearl blockchain's white paper (Pearl Research Team), giving a systematic sensitivity characterization as an alternative to its Jackpot policy, along with efficient algorithm for verifying the sensitivity condition. Beyond its …
Anirban Ghatak, Kaushik Sarkar, Anupam Chattopadhyay, Ambrish Awasthi, Indivar Gupta · 2026-10-18
The stream cipher Espresso was designed by E. Dubrova and M. Hell as a hardware-efficient candidate for 5G security. It has two components - a 256-bit binary non-linear feedback shift register (NFSR), with 14 feedback taps, and a 20-variable non-linear output function. However, t…
Md. Emran Biswas, Md. Delowar Hossain, Mst. Tanbin Yasmin Tanny, Muhammad Aminur Rahaman, Md Al Amin and others · 2026-10-18
Attacks using ransomware have developed into complex multiphase campaigns that target vital infrastructure, resulting in annual damages of billions of dollars. Conventional detection techniques are ineffective against zero-day variations, and privacy issues are raised by centrali…
Duc-Huy Nguyen, Bui Duc Manh, Chi-Hieu Nguyen, Dinh Thai Hoang, Diep N. Nguyen and others · 2026-10-18
Cloud-assisted image classification enables many mobile AI applications, but transmitting raw images to the cloud raises significant privacy concerns. Homomorphic encryption (HE) allows computation over encrypted data; however, existing end-to-end HE-based inference pipelines inc…
GET https://store.agentexchange.work/gw/papers/latest?cat=cs.CR&limit=25 (0.003 USD per call). Catalogue