Adversarial Attacks

Follow this topic Ask about this topic

Adversarial attacks study how deliberately chosen inputs, training data, model parameters, or system interactions can make AI systems fail or behave as intended by an attacker. Common approaches include gradient-based perturbations, black-box query and evolutionary search, generative or semantic changes, physical patches and sensor interference, and poisoning or backdoors. Work spans image, language, audio, graph, and time-series models as well as federated learning, recommenders, robotics, and AI agents, with evaluations on benchmarks and increasingly realistic deployment settings. A central tension is that attacks must be effective and stealthy under practical constraints, while defenses and benchmarks must keep pace with adaptive threats and distinguish digital robustness from real-world resilience.

Latest papers

451 papers54 papers in the last four weeks, up 69% on the four weeks before. 0.3% of all new papers.

Adversarial SQL Injection Generation with LLM-Based Architectures
May 11, 2026Ali Karakoc, H. Birkan YilmazRetrieval-Augmented Generation Adversarial Attacks
Department of Computer Engineering, NETLAB, Bogazici University, Istanbul, Turkey.
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
May 11, 2026Mengqi He, Xinyu Tian, Xin Shen +6Adversarial Attacks on VLMs Adversarial Attacks
Australian National University, ACT, Australia · The University Of Queensland, Brisbane, Queensland, Australia · GE research, Niskayuna, New York, USA +2
Skill Description Deception Attack against Task Routing in Internet of Agents
May 11, 2026Jiayi He, Xiaofeng Luo, Jiawen Kang +3Adversarial Attacks AI Agent Security
School of Automation Guangdong University of Technology Guangzhou, China · College of Computing and Data Science Nanyang Technological University Singapore, Singapore · The State Key Laboratory of Public Big Data Guizhou University Guiyang, China +1
AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
May 9, 2026Tingxi Li, Mingfang Ji, Ravishka Shemal Rathnasuriya +3Efficient Neural Network Inference Adversarial Attacks
The University of Texas at Dallas · Tianjin University
Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression
May 9, 2026Jiaming Liang, Chi-Man Pun, Weisi Lin +1Learned Image Compression Adversarial Attacks
University of Macau Macau, China · Nanyang Technological University Singapore
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
May 9, 2026Kewei Chen, Yayu Long, Shuai Li +1Adversarial Attacks Adversarial Attacks on VLA Models
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences · Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
Hybrid Quantum-Classical GANs for the Generation of Adversarial Network Flows
May 7, 2026Prateek Paudel, Nitin Jha, Abhishek Parakh +1Adversarial Attacks Network Intrusion Detection
Kennesaw State University, Marietta, GA, USA · University of Nebraska Omaha, Omaha, NE, USA
Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation
May 7, 2026Tran Gia Bao Ngo, Zulfikar Alom, Federico Errica +2Graph Neural Networks Adversarial Attacks
Department of Computer Science, University of Manitoba · University of Toledo · NEC Laboratories Europe +2
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
May 5, 2026Jonathan Steinberg, Oren GalLanguage Model Safety Evaluation AI Coding Agents
Swarms & AI Lab (SAIL), University of Haifa
TsallisPGD: Adaptive Gradient Weighting for Adversarial Attacks on Semantic Segmentation
May 5, 2026Alexander Matyasko, Xin Lou, Indriyati Atmosukarto +1Adversarial Attacks Adaptive Loss Weighting
Singapore Institute of Technology, Singapore
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
May 3, 2026Zhiyang Dai, Yansong Gao, Boyu Kuang +5Contrastive Learning Dataset Watermarking
School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · University of Western Australia, Perth, Australia · College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China +3
Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models
May 2, 2026Amin Bigdeli, Amir Khosrojerdi, Radin Hamidi Rad +3Learning to Rank Adversarial Attacks
University of Waterloo, Canada · University of Toronto, Canada · Mila – Quebec AI Institute, Canada +1
Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
May 2, 2026Jiabei Zhang, Ziyuan Yang, Andrew Beng Jin Teoh +1Adversarial Training Adversarial Attacks
School of Cyber Science and Engineering, Sichuan University · Lee Kong Chian School of Medicine, Nanyang Technological University · School of Electrical and Electronic Engineering, Yonsei University
When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
May 1, 2026Lingxi Zhang, Guangtao Zheng, Hanjie ChenAdversarial Attacks Language Model Robustness
1Rice University · University of Virginia
Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
May 1, 2026Alexander Warnecke, Konrad RieckAdversarial Attacks Adversarial Examples
1BIFOLD & TU Berlin
Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models
May 1, 2026Hongrui Zheng, Liejun Wang, Zhiqing GuoAdversarial Attacks Adaptive Loss Weighting
School of Computer Science and Technology, Xinjiang University, Urumqi, China · Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi, China · Silk Road Multilingual Cognitive Computing International Cooperation Joint Laboratory, Xinjiang University, Urumqi, China
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
May 1, 2026An Huang, Junggab Son, Zuobin XiongAdversarial Attacks Diffusion Models
Department of Computer Science, University of Nevada Las Vegas, Las Vegas, USA.
Attention Is Where You Attack
Apr 30, 2026Aviral Srivastava, Sourav PandaSelf-Attention Adversarial Attacks
Amazon · The Pennsylvania State University
Low Rank Adaptation for Adversarial Perturbation
Apr 30, 2026Han Liu, Shanghao Shi, Yevgeniy Vorobeychik +2Adversarial Attacks Low-Rank Approximation
Washington University in St. Louis
One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations
Apr 28, 2026Ravikumar Balakrishnan, Sanket MendaparaVLM Evaluation VLM Robustness
Cisco Systems
Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
Apr 26, 2026Xinyu Zeng, Xiangkun He, Lei Tao +2Flow Matching End-to-End Autonomous Driving
Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China · School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798 · School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
Apr 25, 2026Jingyu Zhang, Jacky Wai Keung, Yan Xiao +3End-to-End Autonomous Driving Adversarial Attacks
Department of Computer Science, City University of Hong Kong, Hong Kong SAR · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China
Adversarial Malware Generation in Linux ELF Binaries via Semantic-Preserving Transformations
Apr 24, 2026Lukáš Hrdonka, Martin JurečekAdversarial Attacks Malware Classification
Faculty of Information Technology, Czech Technical University in Prague, Thákurova 9, Prague, Czech Republic
Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective
Apr 24, 2026Olha Jurečková, Martin Jureček, Matouš Kozák +1Adversarial Attacks Adversarial Robustness
Faculty of Information Technology, Czech Technical University in Prague, Th´akurova 9, Prague, 16000, Czech Republic
Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems
Apr 24, 2026Junsong Xie, Yonghui Yang, Pengyang Shao +1Sharpness-Aware Minimization Adversarial Attacks
Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, Hefei 230009, China · Intelligent Interconnected Systems Laboratory of Anhui Province, Hefei University of Technology, Hefei 230009, China · Laboratory of NExT++, National University of Singapore, Singapore
Adversarial Evasion in Non-Stationary Malware Detection: Minimizing Drift Signals through Similarity-Constrained Perturbations
Apr 23, 2026Pawan Acharya, Lan ZhangConcept Drift Adversarial Attacks
Northern Arizona University, Flagstaff, AZ, USA
Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
Apr 22, 2026Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo +2Randomized Smoothing Adversarial Attacks
Department of Computer Applications, Cochin University of Science and Technology, India · Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Adolfo Ferrata 5, 27100, Pavia, Italy
PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
Apr 21, 2026Dazhuang Liu, Yanqi Qiao, Rui Wang +2Adversarial Attacks Vision Transformer
Delft University of Technology, Delft, the Netherlands. · University of Turku, Turku, Finland
Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
Apr 20, 2026Wenpeng XuAdversarial Attacks Computer-Use Agents
University of California, San Diego
Perturbation Sensitivity of Maximum-Likelihood Pairwise Ranking in Computational Decision Systems
Apr 20, 2026Junyi Yao, Zihao Zheng, Jiayu LongAlgorithmic Auditing Learning to Rank
Washington University in St. Louis USA

May 11, 2026J/K move · Enter open · S save

Adversarial SQL Injection Generation with LLM-Based Architectures

Ali Karakoc, H. Birkan Yilmaz

Department of Computer Engineering, NETLAB, Bogazici University, Istanbul, Turkey.

Retrieval-Augmented Generation Adversarial Attacks Cybersecurity LLMs for Cybersecurity

Open paper AskPDF arXiv

SQL injection (SQLi) attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project (OWASP) Top 10 threats. Today, with advances in Artificial Intelligence (AI), especially in Large Language Models (LLMs), an opportunity has been created for automating adversarial attack tests to measure the defense mechanisms. In this paper, we aim to create a comprehensive evaluation of use cases that utilize LLMs for adversarial SQL injection generation. We introduce two novel LLM-based systems, Retrieval Augmented Generation for Adversarial SQLi (RADAGAS) and Reflective Chain-of-Thought SQLi (RefleXQLi), and compare them with existing baselines against 10 Web Application Firewalls (WAFs) and one execution-based MySQL validator. To perform a comprehensive test, we used six rule-based open-source WAFs (ModSecurity PL1--3, Coraza PL1--3), 2 AI/ML-based WAFs (WAF Brain, CNN-WAF), and 2 commercial WAFs (AWS WAF and Cloudflare WAF). For the LLM models, we used GPT-4o, Claude 3.7 Sonnet, and DeepSeek R1. Our tests consist of 240 experiments that generate 240,000 payloads and perform 2.2 million tests against WAFs. Our comprehensive evaluation reveals that RADAGAS-GPT4o outperforms other baseline models with a 22.73% bypass rate. The proposed RADAGAS variants are highly successful on AI/ML-based WAFs (92.49% on WAF-Brain by RADAGAS-DeepSeek, 80.48% on CNN-WAF by RADAGAS-Claude), but struggle to bypass rule-based WAFs (0--5.70% on ModSecurity and Coraza). In addition to these findings, another observation is that creating less diverse payloads achieves more bypasses, however they show poor results if the initially chosen payload is not successful. We observe that our findings provide a comprehensive view on using LLM-based approaches in security testing.