English
Related papers

Related papers: Semantic Intent Fragmentation: A Single-Shot Compo…

200 papers

In the inference attacks studied in Quantitative Information Flow (QIF), the adversary typically tries to interfere with the system in the attempt to increase its leakage of secret information. The defender, on the other hand, typically…

Cryptography and Security · Computer Science 2023-07-19 Mário S. Alvim , Konstantinos Chatzikokolakis , Yusuke Kawamoto , Catuscia Palamidessi

We present a novel class of jailbreak adversarial attacks on LLMs, termed Task-in-Prompt (TIP) attacks. Our approach embeds sequence-to-sequence tasks (e.g., cipher decoding, riddles, code execution) into the model's prompt to indirectly…

Cryptography and Security · Computer Science 2025-06-03 Sergey Berezin , Reza Farahbakhsh , Noel Crespi

Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety implications of orchestrator invisibility have never been…

Artificial Intelligence · Computer Science 2026-05-15 Hiroki Fukui

Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-12 Fernando Koch , Aladin Djuhera , Alecio Binotto

AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…

Multiagent Systems · Computer Science 2026-01-22 Gopal Vijayaraghavan , Prasanth Jayachandran , Arun Murthy , Sunil Govindan , Vivek Subramanian

The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring their safe deployment. We present SIRAJ: a generic…

Cryptography and Security · Computer Science 2025-10-31 Kaiwen Zhou , Ahmed Elgohary , A S M Iftekhar , Amin Saied

This paper demonstrates that Semantic Context (SC), leveraging descriptive tool information, is a foundational component for robust tool orchestration. Our contributions are threefold. First, we provide a theoretical foundation using…

Machine Learning · Computer Science 2025-07-16 Robert Müller

Large language models (LLMs) are increasingly used as general planners in embodied intelligence, enabling high level coordination and low level task planning for both single robot and multi-robot collaboration. This increasing reliance on…

Robotics · Computer Science 2026-05-19 Zhen Huang , Zhihuang Liu , Mengxuan Luo , Weishang Wu , Zhiping Cai

The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…

Cryptography and Security · Computer Science 2026-03-03 Chuanming Tang , Ling Qing , Shifeng Chen

Space-air-ground integrated networks (SAGIN) promise ubiquitous 6G connectivity but face significant resource management challenges due to heterogeneous infrastructure, dynamic topologies, and stringent quality-of-service (QoS)…

Networking and Internet Architecture · Computer Science 2026-03-18 Linghao Zhang , Haitao Zhao , Bo Xu , Hongbo Zhu , Xianbin Wang

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

Cryptography and Security · Computer Science 2026-01-12 Akshaj Prashanth Rao , Advait Singh , Saumya Kumaar Saksena , Dhruv Kumar

Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long workflows, leading to brittle failures and avoidable tool and API cost. We propose…

Artificial Intelligence · Computer Science 2026-05-15 Yusuke Ozaki , Dhaval Patel

Large Language Models (LLMs) represent valuable intellectual property (IP), reflecting significant investments in training data, compute, and expertise. Deploying these models on partially trusted or insecure devices introduces substantial…

Cryptography and Security · Computer Science 2025-10-30 Racchit Jain , Satya Lokam , Yehonathan Refael , Adam Hakim , Lev Greenberg , Jay Tenenbaum

To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framework. Both theoretically and experimentally, we demonstrate…

Machine Learning · Statistics 2019-07-30 Mingzhang Yin , Mingyuan Zhou

Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…

Cryptography and Security · Computer Science 2025-09-16 Harold Triedman , Rishi Jha , Vitaly Shmatikov

Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…

Cryptography and Security · Computer Science 2026-03-09 Yuxuan Qiao , Dongqin Liu , Hongchang Yang , Wei Zhou , Songlin Hu

Intent-Based Networking (IBN) offers a promising paradigm for intelligent and automated network control in Industrial Internet of Things (IIoT) environments by translating high-level user intents into executable network strategies. However,…

Networking and Internet Architecture · Computer Science 2025-12-25 Shaowen Qin , Jianfeng Zeng , Haodong Guo , Xiaohuan Li , Jiawen Kang , Qian Chen , Dusit Niyato

AI emotional companions face a safety-rapport paradox: restrictive safeguards can damage supportive alliance, while permissive systems risk user harm. We present SLIP (Staged Layers of Intervention Protocol), a four-stage graduated…

Human-Computer Interaction · Computer Science 2026-05-18 Minseo Kim

The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to…

Artificial Intelligence · Computer Science 2026-01-13 Genze Jiang , Kezhi Wang , Xiaomin Chen , Yizhou Huang

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fragility (SFF), a…

Computation and Language · Computer Science 2026-04-03 Katherine Elkins , Jon Chun
‹ Prev 1 4 5 6 7 8 10 Next ›