主题图谱 / cryptography and security

cryptography and security

GeneTech 知识引擎共收录 379 篇相关科研实体，横跨 23 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

相关主题

代表性文献（按质量分排序，前 60 条）

• Consistent attack: Universal adversarial perturbation on embodied vision navigation
  2023 · 具身智能 · Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially …
• Experimental quantum key distribution certified by Bell's theorem
  2022 · 量子计算 · Cryptographic key exchange protocols traditionally rely on computational conjectures such as the hardness of prime factorisation to provide security against eavesdropping attacks. Remarkably, quantum key distribution pro…
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
  2026 · AI 安全与对齐 · Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter do…
• AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
  2026 · AI 安全与对齐 · Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, r…
• Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection
  2026 · AI 安全与对齐 · The proliferation of generative AI poses challenges for information integrity assurance, requiring systems that connect model governance with end-user verification. We present Origin Lens, a privacy-first mobile framewor…
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
  2026 · 具身智能 · Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter do…
• A Survey of Security Challenges and Solutions for Advanced Air Mobility and eVTOL Aircraft
  2026 · 低空经济 · This survey reviews the existing and envisioned security vulnerabilities and defense mechanisms relevant to Advanced Air Mobility (AAM) systems, with a focus on electric vertical takeoff and landing (eVTOL) aircraft. Dra…
• Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
  2025 · AI Agent 生态 · Large language models (LLMs) are evolving into autonomous decision-makers, raising concerns about catastrophic risks in high-stakes scenarios, particularly in Chemical, Biological, Radiological and Nuclear (CBRN) domains…
• Training AI to be Loyal
  2025 · AI 安全与对齐 · Loyal AI is loyal to the community that builds it. An AI is loyal to a community if the community has ownership, alignment, and control. Community owned models can only be used with the approval of the community and shar…
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
  2025 · AI 安全与对齐 · State-of-the-art neural network (NN) verifiers demonstrate that applying the branch-and-bound (BaB) procedure with fast bounding techniques plays a key role in tackling many challenging verification properties. In this w…
• JSTprove: Pioneering Verifiable AI for a Trustless Future
  2025 · AI 安全与对齐 · The integration of machine learning (ML) systems into critical industries such as healthcare, finance, and cybersecurity has transformed decision-making processes, but it also brings new challenges around trust, security…
• Towards Automating Data Access Permissions in AI Agents
  2025 · AI 安全与对齐 · As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conv…
• Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
  2025 · 脑科学 · State-of-the-art neural network (NN) verifiers demonstrate that applying the branch-and-bound (BaB) procedure with fast bounding techniques plays a key role in tackling many challenging verification properties. In this w…
• Measured Hockey-Stick Divergence and its Applications to Quantum Pufferfish Privacy
  2025 · 量子材料 · The hockey-stick divergence is a fundamental quantity characterizing several statistical privacy frameworks that ensure privacy for classical and quantum data. In such quantum privacy frameworks, the adversary is allowed…
• AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images
  2024 · AI 安全与对齐 · Recent advances in the field of generative artificial intelligence (AI) have blurred the lines between authentic and machine-generated content, making it almost impossible for humans to distinguish between such media. On…
• Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
  2023 · AI 安全与对齐 · Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applicat…
• Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent
  2023 · AI 安全与对齐 · Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for …
• Nik Defense: An Artificial Intelligence Based Defense Mechanism against Selfish Mining in Bitcoin
  2023 · 边缘智能 · The Bitcoin cryptocurrency has received much attention recently. In the network of Bitcoin, transactions are recorded in a ledger. In this network, the process of recording transactions depends on some nodes called miner…
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
  2026 · AI Agent 生态 · Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failu…
• Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility
  2026 · AI Agent 生态 · Identity Security Posture Management (ISPM) is a core challenge for modern enterprises operating across cloud and SaaS environments. Answering basic ISPM visibility questions, such as understanding identity inventory and…
• MRMMIA: Membership Inference Attacks on Memory in Chat Agents
  2026 · AI Agent 生态 · Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily f…
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
  2026 · AI Agent 生态 · Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external …
• HearthNet: Edge Multi-Agent Orchestration for Smart Homes
  2026 · AI Agent 生态 · Smart-home users increasingly want to control their homes in natural language rather than assemble rules, dashboards, and API integrations by hand. At the same time, real deployments are brittle: devices fail, integratio…
• Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents
  2026 · AI Agent 生态 · The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace traditional human review capacity. While prior…
• Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
  2026 · AI Agent 生态 · GitHub Actions is increasingly used to deploy LLM-based agents for repository-centric tasks such as issue triage, pull-request review, code modification, and release assistance. These agentic workflows extend traditional…
• An Agentic Workflow for Detecting Personally Identifiable Information in Crash Narratives
  2026 · AI Agent 生态 · Crash narratives in crash reports provide crucial contextual information for traffic safety analysis. Yet, their broader use is hindered by the presence of personally identifiable information (PII), including names, home…
• Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
  2026 · AI Agent 生态 · Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code review and data synchronization. While b…
• Agents at Risk: How Users Unwittingly Undermine LLM Safety
  2026 · AI Agent 生态 · Large language model (LLM)-based agents are increasingly deployed in applications, such as trip-planning agents and web-use agents, to perform complex planning and execution tasks. Prior work has shown that LLM-based age…
• SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
  2026 · AI Agent 生态 · LLM agents increasingly rely on reusable skills (e.g., SKILL markdown files) to execute complex tasks, yet these artifacts lack portability: agent frameworks are highly sensitive to prompt formatting, leading to a large …
• A Framework for Formalizing LLM Agent Security
  2026 · AI Agent 生态 · Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective i…
• Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
  2026 · 智慧农业 · With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant. We observe that changing the precision of an A…
• What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
  2026 · AI 安全与对齐 · Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation, a traffic class that is neither and that binary classifiers structur…
• Neuro-Symbolic Participation Governance for Verifiable AI Agents in Open Digital Twin Ecosystems
  2026 · AI 安全与对齐 · Autonomous AI agents, increasingly empowered by large language models, are becoming important components of human-machine systems for high-stakes decision support in digital twin ecosystems. However, existing multi-agent…
• Explainable Attention-Based LSTM Framework for Early Detection of AI-Assisted Ransomware via File System Behavioral Analysis
  2026 · AI 安全与对齐 · Ransomware continues to evolve as one of the most disruptive cyber threats, with recent variants increasingly leveraging automated and AI-assisted techniques to evade traditional signature-based defenses. Early detection…
• Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework
  2026 · AI 安全与对齐 · As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that …
• ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI
  2026 · AI 安全与对齐 · Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However,…
• ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study
  2026 · AI 安全与对齐 · Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lacks a common classification scheme for comparing these design choices. …
• SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
  2026 · AI 安全与对齐 · DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs) that leverage recent advances in AI -- particularly large language models (LL…
• Crypto x AI, AI x Crypto: A Survey
  2026 · AI 安全与对齐 · The intersection of crypto x AI is spawning papers, products, online posts, and companies. All the surrounding buzz, though, obscures what exactly has been done, what the opportunities and challenges are, and what open q…
• eBPF-Based Cybersecurity Mechanisms: A Systematic Literature Review
  2026 · AI 安全与对齐 · Extended Berkeley Packet Filter (eBPF) has emerged as a kernel-level framework enabling dynamic security enforcement in modern operating systems. While eBPF's cybersecurity potential has attracted significant attention, …
• Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
  2026 · AI 安全与对齐 · While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off b…
• PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM
  2026 · AI 安全与对齐 · Artificial intelligence systems introduce complex privacy risks throughout their lifecycle, especially when processing sensitive or high-dimensional data. Beyond the seven traditional privacy threat categories defined by…
• Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models
  2026 · AI 安全与对齐 · Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, w…
• From Preventive to Reactive: How AI Coding Assistants Transform Developers' Security Awareness
  2026 · AI 安全与对齐 · AI coding assistants are now central to professional software development, yet their impact on how developers think about and practice security remains poorly understood. While prior work has documented vulnerability rat…
• Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
  2026 · AI 安全与对齐 · AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety al…
• Technology-Enhanced Tabletop Exercises for Cybersecurity Education: Lessons Learned
  2026 · AI 安全与对齐 · This innovative practice full paper examines the integration of technology-enhanced tabletop exercises (TTXs) into computing education, focusing on cybersecurity curricula. The motivation is to better prepare students fo…
• AgentDID: Trustless Identity Authentication for AI Agents
  2026 · AI 安全与对齐 · AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical …
• DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
  2026 · AI 安全与对齐 · Domain Generation Algorithms (DGAs) evolve continuously to evade botnet detection, posing a persistent challenge for dependable network defense. While deep learning-based detectors achieve strong performance under static…
• MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoising
  2026 · AI 安全与对齐 · AI watermarking embeds invisible signals within images to provide provenance information and identify content as AI-generated. In this paper, we introduce MarkSweep, a novel watermark removal attack that effectively eras…
• The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
  2026 · AI 安全与对齐 · The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniq…
• Your Space is My Zone: Demystifying the Security Risks of AI-Powered Applications on Pre-Trained Model Hubs
  2026 · AI 安全与对齐 · AI-powered Applications (AI-Apps), hosted on platforms such as Hugging Face, are democratizing access to pre-trained models through online inference and fine-tuning services. While lowering AI adoption barriers, these pl…
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
  2026 · AI 驱动科学发现 · Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failu…
• Firmware Distribution as Attack Surface: A Security Study of ASIC Cryptocurrency Miners
  2026 · 地外矿物 · ASIC cryptocurrency miners are a core component of blockchain infrastructures, directly converting computation and energy into monetary value. Despite their economic importance, their security is rarely evaluated in a st…
• Digital Twin Enabled Simultaneous Learning and Modeling for UAV-assisted Secure Communications with Eavesdropping Attacks
  2026 · 数字孪生 · This paper focuses on secure communications in UAV-assisted wireless networks, which comprise multiple legitimate UAVs (LE-UAVs) and an intelligent eavesdropping UAV (EA-UAV). The intelligent EA-UAV can observe the LE-UA…
• bioETH-Beacon: A Confidential On-Chain Genomic Beacon with Encrypted Counts, Filters, and Bounded Noise over a Fully Homomorphic EVM
  2026 · 生命科学 · The Global Alliance for Genomics and Health (GA4GH) Beacon protocol lets researchers ask whether a genomic variant has been observed in a participating cohort and receive aggregate variant-level counts. As Beacon network…
• Spying Across Chiplets: Side-Channel Attacks in 2.5/3D Integrated Systems
  2026 · 半导体与先进封装 · Advanced packaging and chiplet-based integration are increasingly adopted to build complex heterogeneous systems beyond the limits of monolithic scaling. While these architectures offer major benefits in terms of modular…
• Hardware Design and Security in the Era of Chiplets and LLMs
  2026 · 半导体与先进封装 · The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While the…
• GOD model: Privacy Preserved AI School for Personal Assistant
  2025 · AI Agent 生态 · Personal AI assistants (e.g., Apple Intelligence, Meta AI) offer proactive recommendations that simplify everyday tasks, but their reliance on sensitive user data raises concerns about privacy and trust. To address these…
• Bilevel Optimization for Covert Memory Tampering in Heterogeneous Multi-Agent Architectures (XAMT)
  2025 · AI Agent 生态 · The increasing operational reliance on complex Multi-Agent Systems (MAS) across safety-critical domains necessitates rigorous adversarial robustness assessment. Modern MAS are inherently heterogeneous, integrating conven…
• PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection
  2025 · AI Agent 生态 · Phishing websites remain a major cybersecurity threat, exploiting deceptive structures, brand impersonation, and social engineering to evade detection. Recent advances in large language models (LLMs) have improved phishi…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl http://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl http://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。