English
Related papers

Related papers: Gaming the Metric, Not the Harm: Certifying Safety…

200 papers

Consider a scenario where a harmfulness evaluation metric intended to filter unsafe responses from a Large Language Model. When applied to individual harmful prompt-response pairs, it correctly flags them as unsafe by assigning a high-risk…

Artificial Intelligence · Computer Science 2025-02-14 Ora Nova Fandina , Leshem Choshen , Eitan Farchi , George Kour , Yotam Perlitz , Orna Raz

The Smatch metric is a popular method for evaluating graph distances, as is necessary, for instance, to assess the performance of semantic graph parsing systems. However, we observe some issues in the metric that jeopardize meaningful…

Computation and Language · Computer Science 2025-10-17 Juri Opitz

A connected and automated vehicle safety metric determines the performance of a subject vehicle (SV) by analyzing the data involving the interactions among the SV and other dynamic road users and environmental features. When the data set…

Robotics · Computer Science 2022-04-19 Bowen Weng , Linda Capito , Umit Ozguner , Keith Redmill

Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety…

Machine Learning · Computer Science 2022-06-20 Matteo Papini , Matteo Pirotta , Marcello Restelli

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this…

Artificial Intelligence · Computer Science 2025-12-16 Enhong Mu , Minami Yoda , Yan Zhang , Mingyue Zhang , Yutaka Matsuno , Jialong Li

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

Artificial Intelligence · Computer Science 2026-05-26 Alfredo Metere

A barrier certificate, defined over the states of a dynamical system, is a real-valued function whose zero level set characterizes an inductively verifiable state invariant separating reachable states from unsafe ones. When combined with…

Logic in Computer Science · Computer Science 2024-03-06 Vishnu Murali , Ashutosh Trivedi , Majid Zamani

Embedded Systems (ES) development has been historically focused on functionality rather than security, and today it still applies in many sectors and applications. However, there is an increasing number of security threats over ES, and a…

Cryptography and Security · Computer Science 2021-12-13 Ángel Longueira-Romero , Rosa Iglesias , David Gonzalez , Iñaki Garitano

Software built on poor structural patterns often shows higher exposure to security defects. When code differs from established best practices, verification and maintenance become increasingly difficult, thereby raising the risk of…

Cryptography and Security · Computer Science 2026-01-26 Masoud Jamshidiyan Tehrani

Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify…

The performance of a reinforcement learning algorithm can vary drastically during learning because of exploration. Existing algorithms provide little information about the quality of their current policy before executing it, and thus have…

Machine Learning · Computer Science 2019-05-29 Christoph Dann , Lihong Li , Wei Wei , Emma Brunskill

Ensuring safe interactions in human-centric environments requires robots to understand and adhere to constraints recognized by humans as "common sense" (e.g., "moving a cup of water above a laptop is unsafe as the water may spill" or…

Robotics · Computer Science 2025-04-10 Lukas Brunke , Yanni Zhang , Ralf Römer , Jack Naimer , Nikola Staykov , Siqi Zhou , Angela P. Schoellig

With the advent of smart grid (SG) systems, electricity networks have been able to ensure greater efficiency and utility by interconnecting their grids through cloud-based technology. As SGs become increasingly complex, a wide range of…

Cryptography and Security · Computer Science 2024-04-16 Yussuf Ahmed , Micheal Ezealor , Haitham Mahmoud , MohamedAjmal Azad , Mohamed BenFarah , Mehdi Yousefi

Ensuring the safety of reinforcement learning (RL) policies in high-stakes environments requires not only formal verification but also interpretability and targeted falsification. While model checking provides formal guarantees, its…

Artificial Intelligence · Computer Science 2025-06-05 Tuan Le , Risal Shefin , Debashis Gupta , Thai Le , Sarra Alqahtani

The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers,…

Machine Learning · Computer Science 2026-03-10 Valentin Lafargue , Adriana Laurindo Monteiro , Emmanuelle Claeys , Laurent Risser , Jean-Michel Loubes

Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user views (impressions) that went to content violating a given policy on a given day. Accurate…

Machine Learning · Computer Science 2026-02-24 Attila Dobi , Aravindh Manickavasagam , Benjamin Thompson , Xiaohan Yang , Faisal Farooq

Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as a mitigation where given an input $\mathbf{x}$, a…

Cryptography and Security · Computer Science 2024-09-10 Jiankai Jin , Olga Ohrimenko , Benjamin I. P. Rubinstein

Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. However, existing control techniques often assume access to…

Systems and Control · Electrical Eng. & Systems 2025-06-24 Haoming Jing , Yorie Nakahira

Secure orchestration is an important concern in the internet of service. Next to providing the required functionality the composite services must also provide a reasonable level of security in order to protect sensitive data. Thus, the…

Cryptography and Security · Computer Science 2012-12-18 Gabriele Costa , Fabio Martinelli , Artsiom Yautsiukhin

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Machine Learning · Computer Science 2021-02-24 Elan Rosenfeld , Ezra Winston , Pradeep Ravikumar , J. Zico Kolter
‹ Prev 1 2 3 10 Next ›