Literature surveys, systematizations of knowledge, and meta-analyses
Newest first · 12 reviewed on this page
Search insteadBrynn Knowlton, Jovani Campa, Davide Gallo +2
Generative artificial intelligence (AI) systems—particularly large language models (LLMs)—remain vulnerable to jailbreak attacks: adversarial prompts that bypass safeguards and elicit unsafe or restricted outputs. This survey synthesizes jailbreak research from 2023–2025,…
Juhee Kim, Xiaoyuan Liu, Zhun Wang +4
AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different…
Nyashadzashe Tamuka, T. Mathonsi, T. Olwal +3
Large Language Model (LLM)-based agents integrate various models, including planning loops, memory, tool use, and multi-agent systems, enabling autonomous decision-making through natural-language interfaces. This autonomy also expands the cyberattack surface from model-only…
Javad Forough, Marios Kogias, Hamed Haddadi
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate…
Zehao Lin, Chunyu Li, Kai Chen
Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed without authorization, and propagated…
Yuxi Chen, Junming Chen, Chenyu He +9
As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe computational, collaborative, and security bottlenecks. Current surveys remain fragmented across system optimization, architecture…
Wenjuan Li, Yitao Liu, Runze Chen +1
Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have evolved from data poisoning and weight…
Ziyi Tong, Feifei Sun, Le Minh Nguyen
Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure (PDE) increase due to the scale and opacity of training datasets. PDE refers to…
Richard J. Young, Gregory D. Moody
The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora (AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench, CIRCLE, MOCHA, ASTRA, Scam2Prompt /…
Jinhu Qi, Muzhi Li, Jiahong Liu +9
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 failure modes that challenge trustworthiness. This survey…
Nada Lahjouji, Ashwin Gerard Colaco
Large language model agents increasingly query databases, search document collections, call external APIs, remember past interactions, and act on a user's behalf. As they move from answering questions to operating over sensitive data, privacy becomes harder to enforce. An agent…
Abrar Alotaibi, Moataz Ahmed
Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LLMs), diffusion-based attacks on image classifiers, jailbreak pipelines against vision-language models, and diffusion-based input…
Thi Huyen Nguyen, Zahra Ahmadi
The rapid growth of scientific submissions has pushed traditional peer review toward its scalability limits, motivating the exploration of large language models (LLMs) as intelligent automated evaluation assistants. Although recent studies show that LLMs can generate fluent…
Seyed Bagher Hashemi Natanzi, Bo Tang
Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environments, robotic systems, security-operation workflows, and autonomous agents that can read private data, call tools, write files,…
Yiwei Xu, Yong Zhuang, Xuanming Liu +6
Large language model (LLM) agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial value while simultaneously expanding the security attack surface. This survey provides a comprehensive overview of the…
Xi Li, Shu Zhao, Xiaohan Zou +6
Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Increased model complexity and…
Rabimba Karanjai, Yang Lu, Nour Diallo +4
AI agents increasingly act rather than merely read: across the Model Context Protocol (MCP) ecosystem, the share of deployed tools that modify external state has risen from 27% to 65% of tool use. When agents exercise this authority on public blockchains through MCP, skills, and…
Minh Tran, Cuong Dang, Tuc Nguyen +10
Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introduces new robustness and security risks, including corpus…
Ozgur Kara, Tarik Can Ozden, Furkan Horoz +6
Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse at scale, motivating a rapidly growing body of research on adversarial attacks and defenses. This survey provides, to our…
Miguel Zabaleta, Baihan Lin
Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations,…
George Fatouros, Konstantinos Mavrogiorgos, Georgios Makridis +2
The rapid evolution of Large Language Models (LLMs) has opened new frontiers in cybersecurity automation, enabling intelligent agents capable of multi-step reasoning, tool invocation, and autonomous decision-making across complex security tasks. While individual applications…
P. Mekala, Yonas Kassa, Sushma Mishra
The convergence of Large Language Models (LLMs) with the Internet of Things (IoT) is driving a transformative shift toward a continuous, context-aware smart healthcare ecosystem. Due to its novelty, existing research in this domain remains fragmented, leaving a critical gap in…
Mahmoud E. Farfoura, M. Alia, Ibrahim Mashal +2
The role of AI pair programmers has expanded from local code completion to active participation in the development environment. Contemporary tools can interpret repository context, edit multiple files, call package managers, execute terminal commands, and communicate with…
De-Yu Meng, Tad Gonsalves
With the explosive growth of large language models (LLMs), research on machine-generated text detection (MGTD) has also proliferated. Alongside these developments, a wide range of attack algorithms targeting MGTD systems have emerged. While previous studies have surveyed…
Rui-Zhan Xue, Fang He, Hui-Min Deng +2
Jie-Qun Wei, Yuejin Zhang
With the rapid growth of digital information, the risk of sensitive information leakage in textual data, including personally identifiable information, medical privacy, financial data, and corporate confidential information, has become increasingly prominent. Traditional…
Junchen Ding, Jialiang Dong, Yi Zhu +5
The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the unchecked proliferation of"AI slop."These artifacts, hallucinated vulnerabilities, plausible but incorrect…
Sana Mourad, E. E. Abdallah, Mohammad Ababneh
Current language model deployments face growing security challenges from prompt-based attacks, including jailbreaks, direct and indirect prompt injection, and instruction hijacking, which often evade traditional rule-based safeguards. As these models are increasingly integrated…
Jiawei Liu, Jiacheng Guo, Tian Zhang +4
Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks,…
Baiqi Wu, Qing-Ming Li, Chun-Yi Zhou +2
Rapid AI development across industries raises pressing security and privacy risks. This work presents a unified comparison of large language models, AI agents, and embodied agents, introducing a taxonomy of risks spanning data, models, systems, content, and applications,…
Nathaniel Kang, Jongho Im
The rapid enterprise adoption of Large Language Models (LLMs) has generated an expanding attack surface that existing surveys address monolithically, leaving engineering practitioners without deployment-specific guidance. This survey organizes the LLM security and governance…
Markov Grey, Charbel-Raphaël Ségerie
As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for estimating model capabilities, they often…
Yanxu Mao, Tiehan Cui, Peipei Liu +2
Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a systematic survey of the growing…
Zimo Ji, Xunguang Wang, Zongjie Li +6
Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt Injection (IPI) attacks that hijack their tool calls. In response, numerous IPI-centric defense frameworks have emerged. However, these…
Xinyu Huang, B. ShyamKarthickV, Taozhao Chen +6
The integration of Large Language Models (LLMs) into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities stemming from the''embodiment gap'', a…
Boxin Wang, Weixin Chen, Hengzhi Pei +7
Comprehensive trustworthiness evaluation of GPT models across 8 dimensions including toxicity, bias, robustness, privacy, fairness, and machine ethics.
Yifan Yao, Jinhao Duan, Kaidi Xu +3
Comprehensive survey covering LLM security and privacy from three perspectives: beneficial applications of LLMs for security, attacks against LLMs, and defensive techniques.
Lichao Sun, Yue Huang, Haoran Wang +2
Comprehensive study of LLM trustworthiness across truthfulness, safety, fairness, robustness, privacy, and machine ethics with benchmarks.
Yi Liu, Gelei Deng, Yuekang Li +6
First comprehensive survey of prompt injection attacks against LLM-integrated applications, categorizing attacks and defenses with a unified framework.
Leo Schwinn, David Dobre, Stephan Gunnemann +1
Systematizes adversarial attacks and defenses for LLMs, connecting them to the classical adversarial ML literature while identifying LLM-specific threats.
Aysan Esmradi, Daniel Wankit Yip, Chun Fai Chan
Surveys attack techniques across the LLM lifecycle including training, fine-tuning, and inference, with comprehensive mitigation strategies.
Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan +2
Surveys machine unlearning techniques for LLMs including methods for forgetting specific training data, complying with data deletion requests, and maintaining model utility.
Feng He, Tianqing Zhu, Dayong Ye +3
Surveys security and privacy challenges specific to LLM-based agents, covering agent architectures, attack surfaces, and defense mechanisms.
Rob van der Veer, OWASP AI Exchange Team
Comprehensive guide for AI security and privacy including threat analysis, controls, and regulatory mapping for AI systems.
Apostol Vassilev, Alina Oprea, Alie Fordyce +1
NIST's authoritative taxonomy of adversarial ML attacks and mitigations covering evasion, poisoning, privacy, and abuse attacks against AI systems.
Ken Huang, Yang Wang, Ben Goertzel +3
Comprehensive textbook covering generative AI security from foundations to advanced topics including LLM threats, defenses, privacy, and governance.
Clark Barrett, Brad Boyd, Elie Burzstein +20
Comprehensive treatment of generative AI security risks across the ML lifecycle with a focus on practical mitigations and deployment considerations.