AI
Artificial intelligence: machine learning, neural networks, large language models, deep learning, AI research, and AI tools.
-
Privacy Auditing with One (1) Training Run neurips.cc
(NeurIPS - best paper) A scheme for auditing differentially private machine learning systems with a single training run.
-
Membership Inference Attacks Against Machine Learning Models ieeexplore.ieee.org
(Symposium on Security and Privacy) Given a machine learning model and a record, determine whether this record was used as part of the model's training dataset or not.
-
Stealing Knowledge from Protected Deep Neural Networks Using Composite Unlabeled Data ieeexplore.ieee.org
(ICNN) Composite method which can be used to attack and extract the knowledge ofa black box model even if it completely conceals its softmaxoutput.
-
Under manipulations, are some AI models harder to audit? grodino.github.io
(SATML) Relates the difficulty of black-box audits to the capacity of the targeted models, using the Rademacher complexity.
-
Neural Network Inversion in Adversarial Setting via Background Knowledge Alignment dl.acm.org
(CCS) Model inversion approach in the adversary setting based on training an inversion model that acts as aninverse of the original model. With no fullknowledge about the original training data, an accurate inversion is still possible by training the inversion model on…
-
Practical Black-Box Attacks against Machine Learning dl.acm.org
(Asia CCS) Understand how vulnerable is a remote service to adversarial classification attacks.
-
The Fair Game: Auditing & debiasing AI algorithms overtime cambridge.org
(Cambridge Forum on AI: Law and Governance) Aims to simulate the evolution of ethical and legal frameworks in the society by creating an auditor which sends feedback to a debiasing algorithm deployed around an ML system.
-
The Fair Game: Auditing & debiasing AI algorithms over time cambridge.org
Jouarnal of Cambridge Forum on AI: Law and Governance
-
Auditing Pay-Per-Token in Large Language Models arxiv.org
(arXiv) Develops an auditing framework based on martingale theory that enables a trusted third-party auditor who sequentially queries a provider to detect token misreporting.
-
Hardware and software platform inference arxiv.org
(arXiv) A method for identifying the underlying GPU architecture and software stack of a black-box machine learning model solely based on its input-output behavior.
-
FairProof: Confidential and Certifiable Fairness for Neural Networks arxiv.org
(Arxiv) Proposes an alternative paradigm to traditional auditing using crytographic tools like Zero-Knowledge Proofs; gives a system called FairProof for verifying fairness of small neural networks.
-
(ICLR) Considers backdoor detection under the black-box setting in machine learning as a service (MLaaS) applications.
-
Extracting Training Data from Large Language Models arxiv.org
(USENIX Security) Extract verbatim text sequences from the GPT-2 model’s training data.
-
Extracting Training Data from Large Language Models arxiv.org
(arxiv) Performs a training data extraction attack to recover individual training examples by querying the language model.
-
Making targeted black-box evasion attacks effective andefficient arxiv.org
(arXiv) Investigates how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks.
-
Neural Network Model Extraction Attacks in Edge Devicesby Hearing Architectural Hints arxiv.org
(arxiv) Through the acquisition of memory access events from bus snooping, layer sequence identification bythe LSTM-CTC model, layer topology connection according to the memory access pattern, and layer dimension estimation under data volume constraints, it demonstrates one can…
-
Stealing Neural Networks via Timing Side Channels arxiv.org
(arXiv) Stealing/approximating a model through timing attacks usin queries.
-
CALM: Curiosity-Driven Auditing for Large Language Models arxiv.org
(AAAI) Auditing as a black-box optimization problem where the goal is to automatically uncover input-output pairs of the target LLMs that exhibit illegal, immoral, or unsafe behaviors.
-
LLMs hallucinate graphs too: a structural perspective arxiv.org
(complex networks) Queries LLMs for known graphs and studies topological hallucinations. Proposes a structural hallucination rank.
-
Adversarial Model Extraction on Graph Neural Networks arxiv.org
(AAAI Workshop on Deep Learning on Graphs: Methodologies and Applications) Introduces GNN model extraction and presents a preliminary approach for this.
-
TamperNN: Efficient Tampering Detection of Deployed Neural Nets arxiv.org
(ISSRE) Algorithms to craft inputs that can detect the tampering with a remotely executed classifier model.
-
Adversarial Frontier Stitching for Remote Neural Network Watermarking arxiv.org
(Neural Computing and Applications) (Alternative implementation) Check if a remote machine learning model is a "leaked" one: through standard API requests to a remote model, extract (or not) a zero-bit watermark, that was inserted to watermark valuable models (eg, large deep…
-
Towards Reverse-Engineering Black-Box Neural Networks arxiv.org
(ICLR) (Code) Infer inner hyperparameters (eg number of layers, non-linear activation type) of a remote neural network model by analysing its response patterns to certain inputs.
-
StatQuest youtube.com
Introductory video explanations of statistics, probability, and machine learning.
-
Mathematics and AI sites.math.washington.edu
University of Washington Fall 2025 graduate course with public slides, Lean examples, projects, and readings on machine learning, formalization, autoformalization, mathematical discovery, and ethics.
-
AI for Mathematics and Theoretical Computer Science simons.berkeley.edu
Simons Institute and SLMath workshop archive with recorded talks on proof assistants, automated reasoning, machine learning, and mathematical discovery.
-
Probabilistic Machine Learning probml.github.io
Introductory and advanced books by Kevin Murphy, with free draft PDFs, code, figures, exercises, and teaching resources.
-
Mathematics of Machine Learning ocw.mit.edu
Free graduate MIT course on the mathematical and statistical foundations of machine learning, with lecture notes, assignments, and problem-set solutions.
-
Mathematics for Machine Learning mml-book.github.io
Free textbook on the linear algebra, geometry, calculus, probability, and optimization needed to study machine learning.
-
Reinforcement Learning: An Introduction mitpress.mit.edu
Richard S. Sutton, Andrew G. Barto (2nd edition).
-
Math AI Seminar math.washington.edu
University of Washington research seminar on formalization, theorem proving, mathematical AI, and machine-learning applications in mathematics, with a multi-year event archive.
-
LeanDojo v2 leandojo.org
Open-source framework and benchmark data for training, evaluating, and deploying AI-assisted theorem provers for Lean 4.
-
b=M²L bm2l.github.io
Barcelona Mathematics and Machine Learning colloquia on the interaction between mathematics and machine learning, with multi-year editions and recorded talks.
-
First Proof Project 1stproof.org
Independent project that publishes research-level problems, evaluation methods, solutions, and expert commentary for assessing AI systems in mathematics.
-
Karpathy's Neural Networks: Zero to Hero youtube.com
Build neural networks and language models from first principles.
-
Speech and Language Processing web.stanford.edu
The continuously updated NLP reference by Dan Jurafsky and James Martin.
-
Reinforcement Learning: An Introduction web.stanford.edu
Sutton and Barto's foundational treatment of reinforcement learning concepts and algorithms.
-
Understanding Deep Learning udlbook.github.io
Theory, intuition, and practical notebooks by Simon Prince.
-
The 100-Page Language Models Book thelmbook.com
A concise, technical introduction by Andriy Burkov.
-
Promptfoo promptfoo.dev
Test cases, assertions, model comparisons, and red-team checks for LLM applications.
-
LLM Engineer's Handbook packtpub.com
LLMOps, fine-tuning, serving, and production workflows.
-
Designing Machine Learning Systems oreilly.com
Scalable, maintainable machine learning systems by Chip Huyen.
-
AI Engineering oreilly.com
Building applications with foundation models by Chip Huyen.
-
Running Agents openai.github.io
Lifecycle, session, exception, and durable-execution patterns in the OpenAI Agents SDK.
-
Human-in-the-Loop openai.github.io
Pause, inspect, approve, reject, and resume tool calls without losing agent state.
-
OpenAI Agents SDK openai.github.io
A small SDK for tools, handoffs, guardrails, tracing, and agent orchestration.
-
Harness Engineering openai.com
OpenAI's field report on building software with coding agents, repository constraints, automated checks, and human steering.
-
Model Context Protocol modelcontextprotocol.io
The open specification for connecting AI applications to external tools, data sources, prompts, and interactive apps.
-
Made With ML madewithml.com
An open course on designing, developing, deploying, and iterating on production ML systems.
-
Hands-On Large Language Models llm-book.com
A visual and practical guide by Jay Alammar and Maarten Grootendorst.
- next page of items loading…
