{"total":108,"rows":[{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2102.05123","title":"Backdoor Scanning for Deep Neural Networks through K-Arm Optimization","created":"2021-02-09","cited_by_count":98,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2102.10496","title":"Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits","created":"2021-02-21","cited_by_count":49,"area":"safety"},{"id":"2111.04625","title":"DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories","created":"2021-11-08","cited_by_count":42,"area":null},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42,"area":null},{"id":"2111.12965","title":"Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks","created":"2021-11-25","cited_by_count":34,"area":null},{"id":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29,"area":null},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"id":"2207.13417","title":"Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips","created":"2022-07-27","cited_by_count":22,"area":null},{"id":"2107.07240","title":"Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting","created":"2021-07-15","cited_by_count":21,"area":null},{"id":"2101.08254","title":"RADAR: Run-time Adversarial Weight Attack Detection and Accuracy Recovery","created":"2021-01-20","cited_by_count":18,"area":null},{"id":"2308.04466","title":"Backdoor Federated Learning by Poisoning Backdoor-Critical Layers","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2305.00097","title":"NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation","created":"2023-04-28","cited_by_count":16,"area":"safety"},{"id":"2308.07934","title":"One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training","created":"2023-08-12","cited_by_count":14,"area":null},{"id":"2207.12405","title":"Versatile Weight Attack via Flipping Limited Bits","created":"2022-07-25","cited_by_count":13,"area":"safety"},{"id":"2103.13813","title":"RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2112.13843","title":"BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch","created":"2021-12-24","cited_by_count":11,"area":null},{"id":"2108.06017","title":"AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learning","created":"2021-08-13","cited_by_count":10,"area":"distill"},{"id":"2411.13757","title":"GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2111.01932","title":"HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks","created":"2021-11-02","cited_by_count":9,"area":null},{"id":"2507.03236","title":"On Jailbreaking Quantized Language Models Through Fault Injection Attacks","created":"2025-07-04","cited_by_count":8,"area":"alignment"},{"id":"2412.06219","title":"Data Free Backdoor Attacks","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2104.08323","title":"Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators","created":"2021-04-16","cited_by_count":6,"area":null},{"id":"2110.07683","title":"Don't Knock! Rowhammer at the Backdoor of DNN Models","created":"2021-10-14","cited_by_count":6,"area":null},{"id":"2204.09514","title":"Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems","created":"2022-04-18","cited_by_count":6,"area":null},{"id":"2204.10933","title":"A Tale of Two Models: Constructing Evasive Attacks on Edge Models","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2306.14043","title":"Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks","created":"2023-06-24","cited_by_count":6,"area":"safety"},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2209.14243","title":"A Closer Look at Evaluating the Bit-Flip Attack Against Deep Neural Networks","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2303.08581","title":"Model Extraction Attacks on Split Federated Learning","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2308.16703","title":"Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models","created":"2023-08-31","cited_by_count":5,"area":null},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2503.21793","title":"Input-Triggered Hardware Trojan Attack on Spiking Neural Networks","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2509.21843","title":"SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2105.03251","title":"Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks","created":"2021-05-05","cited_by_count":4,"area":null},{"id":"2502.07408","title":"Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2503.07505","title":"From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2105.01403","title":"An Overview of Laser Injection against Embedded Neural Network Models","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2109.02018","title":"Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning","created":"2021-09-05","cited_by_count":3,"area":null},{"id":"2111.01080","title":"ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2309.06223","title":"Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2405.02642","title":"Machine Learning in Space: Surveying the Robustness of on-board ML models to Radiation","created":"2024-05-04","cited_by_count":3,"area":null},{"id":"2405.13891","title":"DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2503.10792","title":"Byzantine-Resilient Federated Learning via Distributed Optimization","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2504.13786","title":"On the Relationship Between Robustness and Expressivity of Graph Neural Networks","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2511.02866","title":"LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2304.12876","title":"Evaluation of Parameter-based Attacks against Embedded Neural Networks with Laser Injection","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2305.08034","title":"DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNs","created":"2023-05-14","cited_by_count":2,"area":null},{"id":"2305.09684","title":"Decision-based iterative fragile watermarking for model integrity verification","created":"2023-05-13","cited_by_count":2,"area":"safety"},{"id":"2308.16665","title":"Fault Injection on Embedded Neural Networks: Impact of a Single Instruction Skip","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2405.01741","title":"PVF:Understanding AI Vulnerability Against SDCs","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2502.16286","title":"Verification of Bit-Flip Attacks against Quantized Neural Networks","created":"2025-02-22","cited_by_count":2,"area":null},{"id":"2505.16670","title":"BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2602.17837","title":"TFL: Targeted Bit-Flip Attack on Large Language Model","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2603.08737","title":"Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2108.02416","title":"Aspis: Robust Detection for Distributed Learning","created":"2021-08-05","cited_by_count":1,"area":null},{"id":"2112.03477","title":"BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2406.04809","title":"A Survey of Fragile Model Watermarking","created":"2024-06-07","cited_by_count":1,"area":"safety"},{"id":"2407.21220","title":"DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2411.13459","title":"SoK: A Systems Perspective on Compound AI Threats and Countermeasures","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2503.07568","title":"Runtime Detection of Adversarial Attacks in AI Accelerators Using Performance Counters","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2507.05531","title":"Bit-Flip Fault Attack: Crushing Graph Neural Networks via Gradual Bit Search","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2507.06380","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.17371","title":"SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2512.09872","title":"FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning","created":"2025-12-10","cited_by_count":1,"area":"mllm"},{"id":"2602.16309","title":"The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.10042","title":"Targeted Bit-Flip Attacks on LLM-Based Agents","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2108.10066","title":"Dynamic Neural Network Architectural and Topological Adaptation and Related Methods -- A Survey","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2111.09488","title":"Attacking Deep Learning AI Hardware with Universal Adversarial Perturbation","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2208.08085","title":"Detection and Mitigation of Byzantine Attacks in Distributed Training","created":"2022-08-17","cited_by_count":0,"area":null},{"id":"2211.01808","title":"Dormant Neural Trojans","created":"2022-11-02","cited_by_count":0,"area":"safety"},{"id":"2311.01205","title":"Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2401.16766","title":"Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning","created":"2024-01-30","cited_by_count":0,"area":null},{"id":"2411.08133","title":"Impactful Bit-Flip Search on Full-precision Models","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2504.01933","title":"Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2505.06315","title":"Threat Modeling for AI: The Case for an Asset-Centric Approach","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2512.14715","title":"How a Bit Becomes a Story: Semantic Steering via Differentiable Fault Injection","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.15778","title":"COBRA: Catastrophic Bit-flip Reliability Analysis of State-Space Models","created":"2025-12-14","cited_by_count":0,"area":"ssm"},{"id":"2512.22174","title":"BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.17778","title":"Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.20646","title":"On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.08740","title":"Architectural Design and Performance Analysis of FPGA based AI Accelerators: A Comprehensive Review","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.10753","title":"A PUF-Based Approach for Copy Protection of Intellectual Property in Neural Network Models","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.18120","title":"MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.22770","title":"From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.03753","title":"Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.05743","title":"On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors","created":"2026-04-07","cited_by_count":0,"area":"diffusion"},{"id":"2604.17249","title":"Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems","created":"2026-04-19","cited_by_count":0,"area":"inference"},{"id":"2605.18907","title":"Lightweight and Fast Backdoor Model Detection","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.18908","title":"Fast and Lightweight Backdoor Detection via Head Random Probing","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.04317","title":"Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09548","title":"Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips","created":"2026-06-08","cited_by_count":0,"area":"safety"},{"id":"2607.13088","title":"Securing LLMs in the Wild: Privacy and Security Challenges at the Edge","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2607.17550","title":"(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure","created":"2026-07-20","cited_by_count":0,"area":"safety"},{"id":"2607.19490","title":"Integrity of peer-to-peer distributed LLM inference under malicious nodes","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.15901","title":"Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive","created":"2026-08-16","cited_by_count":0,"area":null}],"next_cursor":"100"}