English
Related papers

Related papers: Retrying vs Resampling in AI Control

200 papers

Malware detection increasingly relies on AI systems that integrate signature-based detection with machine learning. However, these components are typically developed and combined in isolation, missing opportunities to reduce data complexity…

Cryptography and Security · Computer Science 2025-08-14 Andrea Ponte , Luca Demetrio , Luca Oneto , Ivan Tesfai Ogbu , Battista Biggio , Fabio Roli

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input and only share the models outputs for a target task with the server. We study how a…

Machine Learning · Computer Science 2024-10-02 Mohammad Malekzadeh , Deniz Gunduz

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

Computation and Language · Computer Science 2025-01-20 Vinu Sankar Sadasivan , Aounon Kumar , Sriram Balasubramanian , Wenxiao Wang , Soheil Feizi

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance…

Computation and Language · Computer Science 2026-03-31 Rahul Soni

Powered by the increasing predictive capabilities of machine learning algorithms, artificial intelligence (AI) systems have the potential to overrule human mistakes in many settings. We provide the first field evidence that the use of AI…

Machine Learning · Computer Science 2025-02-14 David Almog , Romain Gauriot , Lionel Page , Daniel Martin

Information-flow control mechanisms are difficult both to design and to prove correct. To reduce the time wasted on doomed proof attempts due to broken definitions, we advocate modern random testing techniques for finding counterexamples…

Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…

Computers and Society · Computer Science 2025-02-11 Stephen Barrett , Philip Fox , Joshua Krook , Tuneer Mondal , Simon Mylius , Alejandro Tlaie

Importance sampling (IS) is a popular technique in off-policy evaluation, which re-weights the return of trajectories in the replay buffer to boost sample efficiency. However, training with IS can be unstable and previous attempts to…

Machine Learning · Computer Science 2025-05-20 Chengyang Ying , Zhongkai Hao , Xinning Zhou , Hang Su , Dong Yan , Jun Zhu

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

For many compiled languages, source-level types are erased very early in the compilation process. As a result, further compiler passes may convert type-safe source into type-unsafe machine code. Type-unsafe idioms in the original source and…

Programming Languages · Computer Science 2016-03-22 Matthew Noonan , Alexey Loginov , David Cok

Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchmarks of general intelligence such as the Abstraction and…

Artificial Intelligence · Computer Science 2024-07-02 Natasha Butt , Blazej Manczak , Auke Wiggers , Corrado Rainone , David W. Zhang , Michaël Defferrard , Taco Cohen

Background: Screening trials require large sample sizes and long time-horizons to demonstrate mortality reductions. We recently proposed increasing statistical power by testing stored control-arm specimens, called the Intended Effect (IE)…

Applications · Statistics 2024-11-11 Hormuzd A. Katki , Li C. Cheung

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

Practitioners have reported a directional pattern in AI-assisted code generation: AI-generated code tends to fail quietly, preserving the appearance of functionality while degrading or concealing guarantees. This paper introduces the…

Software Engineering · Computer Science 2026-04-21 William M. Parris

It is not an exaggeration to say that the recent progress in artificial intelligence technology depends on large-scale and high-quality data. Simultaneously, a prevalent issue exists everywhere: the budget for data labeling is constrained.…

Machine Learning · Computer Science 2023-08-22 Yujin Hwang , Won Jo , Juyoung Hong , Yukyung Choi

Rerankers, typically cross-encoders, are computationally intensive but are frequently used because they are widely assumed to outperform cheaper initial IR systems. We challenge this assumption by measuring reranker performance for full…

Information Retrieval · Computer Science 2025-07-14 Mathew Jacob , Erik Lindgren , Matei Zaharia , Michael Carbin , Omar Khattab , Andrew Drozdov

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

Machine Learning · Computer Science 2021-09-03 Jing Lin , Ryan Luley , Kaiqi Xiong

Early identification of security issues in software development is vital to minimize their unanticipated impacts. Code review is a widely used manual analysis method that aims to uncover security issues along with other coding issues in…

Software Engineering · Computer Science 2024-07-18 Wachiraphan Charoenwet , Patanamon Thongtanunam , Van-Thuan Pham , Christoph Treude

AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex criminal activity. Working with law enforcement and policy…