{"list":"other","total":54,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"1912.00049","title":"Square Attack: a query-efficient black-box adversarial attack via random search","created":"2019-11-29","cited_by_count":685},{"id":"1902.06531","title":"STRIP: A Defence Against Trojan Attacks on Deep Neural Networks","created":"2019-02-18","cited_by_count":459},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2012.03816","title":"Invisible Backdoor Attack with Sample-Specific Triggers","created":"2020-12-07","cited_by_count":353},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2110.11571","title":"Anti-Backdoor Learning: Training Clean Models on Poisoned Data","created":"2021-10-22","cited_by_count":263},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"1902.11237","title":"A new Backdoor Attack in CNNs by training set corruption without label poisoning","created":"2019-02-12","cited_by_count":242},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166},{"id":"1611.07476","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","created":"2016-11-22","cited_by_count":159},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145},{"id":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128},{"id":"1512.07666","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","created":"2015-12-23","cited_by_count":121},{"id":"2302.03251","title":"SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency","created":"2023-02-07","cited_by_count":97},{"id":"2205.13383","title":"BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning","created":"2022-05-26","cited_by_count":86},{"id":"1905.13409","title":"Bypassing Backdoor Detection Algorithms in Deep Learning","created":"2019-05-31","cited_by_count":74},{"id":"1909.06872","title":"Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors","created":"2019-09-15","cited_by_count":72},{"id":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70},{"id":"2209.11715","title":"The \"Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices","created":"2022-09-23","cited_by_count":63},{"id":"2312.01037","title":"Eliciting Latent Knowledge from Quirky Language Models","created":"2023-12-02","cited_by_count":62},{"id":"2308.12108","title":"The Local Learning Coefficient: A Singularity-Aware Complexity Measure","created":"2023-08-23","cited_by_count":51},{"id":"2010.11560","title":"Deep Learning is Singular, and That's Good","created":"2020-10-22","cited_by_count":49},{"id":"2303.18191","title":"Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency","created":"2023-03-27","cited_by_count":46},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46},{"id":"2412.09565","title":"Obfuscated Activations Bypass LLM Latent-Space Defenses","created":"2024-12-12","cited_by_count":45},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40},{"id":"2505.18032","title":"Mahalanobis++: Improving OOD Detection via Feature Normalization","created":"2025-05-23","cited_by_count":32},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27},{"id":"2312.02673","title":"Robust Backdoor Detection for Deep Learning via Topological Evolution Dynamics","created":"2023-12-05","cited_by_count":26},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24},{"id":"2502.05475","title":"You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation","created":"2025-02-08","cited_by_count":17},{"id":"2501.17745","title":"Dynamics of Transient Structure in In-Context Linear Regression Transformers","created":"2025-01-29","cited_by_count":14},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14},{"id":"2504.18274","title":"Structural Inference: Interpreting Small Language Models with Susceptibilities","created":"2025-04-25","cited_by_count":13},{"id":"2509.26537","title":"The Loss Kernel: A Geometric Probe for Deep Learning Interpretability","created":"2025-09-30","cited_by_count":9},{"id":"2508.00331","title":"Embryology of a Language Model","created":"2025-08-01","cited_by_count":4},{"id":"2402.11237","title":"Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning","created":"2024-02-17","cited_by_count":1}],"next_cursor":null}