Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such alignment can be bypassed to produce prohibited content using a technique commonly referred to as jailbreak. Different systems have been proposed to perform the jailbreak automatically. These systems rely on evaluation methods to determine whether a jailbreak attempt is successful. However, our analysis reveals that current jailbreak evaluation methods have two limitations. (1) Their objectives lack clarity and do not align with the goal of identifying unsafe responses. (2) They oversimplify the jailbreak result as a binary outcome, successful or not. In this paper, we propose three metrics, safeguard violation, informativeness, and relative truthfulness, to evaluate language model jailbreak. Additionally, we demonstrate how these metrics correlate with the goal of different malicious actors. To compute these metrics, we introduce a multifaceted approach that extends the natural language generation evaluation method after preprocessing the response. We evaluate our metrics on a benchmark dataset produced from three malicious intent datasets and three jailbreak systems. The benchmark dataset is labeled by three annotators. We compare our multifaceted approach with three existing jailbreak evaluation methods. Experiments demonstrate that our multifaceted evaluation outperforms existing methods, with F1 scores improving on average by 17% compared to existing baselines. Our findings motivate the need to move away from the binary view of the jailbreak problem and incorporate a more comprehensive evaluation to ensure the safety of the language model.

The advent of Generative Artificial Intelligence (GenAI) models, including GitHub Copilot, OpenAI GPT, and Stable Diffusion, has revolutionized content creation, enabling non-professionals to produce high-quality content across various domains. This transformative technology has led to a surge of synthetic content and sparked legal disputes over copyright infringement. To address these challenges, this paper introduces a novel approach that leverages the learning capacity of GenAI models for copyright legal analysis, demonstrated with GPT2 and Stable Diffusion models. Copyright law distinguishes between original expressions and generic ones (Sc\`enes \`a faire), protecting the former and permitting reproduction of the latter. However, this distinction has historically been challenging to make consistently, leading to over-protection of copyrighted works. GenAI offers an unprecedented opportunity to enhance this legal analysis by revealing shared patterns in preexisting works. We propose a data-driven approach to identify the genericity of works created by GenAI, employing "data-driven bias" to assess the genericity of expressive compositions. This approach aids in copyright scope determination by utilizing the capabilities of GenAI to identify and prioritize expressive elements and rank them according to their frequency in the model's dataset. The potential implications of measuring expressive genericity for copyright law are profound. Such scoring could assist courts in determining copyright scope during litigation, inform the registration practices of Copyright Offices, allowing registration of only highly original synthetic works, and help copyright owners signal the value of their works and facilitate fairer licensing deals. More generally, this approach offers valuable insights to policymakers grappling with adapting copyright law to the challenges posed by the era of GenAI.

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adversarial examples. While character-level attacks easily maintain semantics, they have received less attention as they cannot easily adopt popular gradient-based methods, and are thought to be easy to defend. Challenging these beliefs, we introduce Charmer, an efficient query-based adversarial attack capable of achieving high attack success rate (ASR) while generating highly similar adversarial examples. Our method successfully targets both small (BERT) and large (Llama 2) models. Specifically, on BERT with SST-2, Charmer improves the ASR in 4.84% points and the USE similarity in 8% points with respect to the previous art. Our implementation is available in https://github.com/LIONS-EPFL/Charmer.

NORAD confirmed it detected four Russian military aircraft in the Alaska Air Defense Identification Zone on Thursday, but the aircraft didn't enter U.S. airspace. Russia said Monday it plans to hold drills simulating the use of battlefield nuclear weapons amid rising tensions following comments by senior Western officials about the possibility of deeper involvement in the war in Ukraine. The announcement came on the eve of Russian President Vladimir Putin's inauguration to a fifth term in office and in a week when Moscow on Thursday will celebrate Victory Day, its most important secular holiday, marking its defeat of Nazi Germany in World War II. The drills are a response to "provocative statements and threats of certain Western officials regarding the Russian Federation," the Defense Ministry said in a statement. PUTIN WARNS THE WEST THAT RUSSIA IS'READY' FOR NUCLEAR WAR: 'WEAPONS EXIST IN ORDER TO USE THEM' It was the first time Russia has publicly announced drills involving tactical nuclear weapons, although its strategic nuclear forces regularly hold exercises.

The White House has issued new rules aimed at companies that manufacture synthetic DNA after years of warnings that a pathogen made with mail-order genetic material could accidentally or intentionally spark the next pandemic. The rules, released on April 29, are the result of an executive order signed by President Joe Biden last fall to establish new standards for AI safety and security, including AI applied to biotechnology. Artificially generated DNA allows researchers to do all sorts of things--develop diagnostic tests, make beneficial enzymes to eat up plastic, or engineer potent antibodies to treat disease--without having to extract natural sequences from organisms. Need to study a rare type of bacteria? Instead of going out into the field to collect a sample, its genetic sequence can simply be ordered from a DNA synthesis company instead.

Here is the situation on Monday, May 6, 2024. At least one person was killed and 24 injured in Russian drone and bomb attacks on Ukraine's northeastern city of Kharkiv and the surrounding region. Power cuts were also reported. Ukraine's Air Force said that Russia had launched 24 Shahed attack drones and 23 were shot down. Russia's Ministry of Defence said its forces had captured the village of Ocheretyne, in Ukraine's eastern Donetsk region.

This review article highlights state-of-the-art data-driven techniques to discover, encode, surrogate, or emulate constitutive laws that describe the path-independent and path-dependent response of solids. Our objective is to provide an organized taxonomy to a large spectrum of methodologies developed in the past decades and to discuss the benefits and drawbacks of the various techniques for interpreting and forecasting mechanics behavior across different scales. Distinguishing between machine-learning-based and model-free methods, we further categorize approaches based on their interpretability and on their learning process/type of required data, while discussing the key problems of generalization and trustworthiness. We attempt to provide a road map of how these can be reconciled in a data-availability-aware context. We also touch upon relevant aspects such as data sampling techniques, design of experiments, verification, and validation.

We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social science problem, since the social sciences enjoy a rich toolkit of models for understanding and aligning motivation and behavior, much of which could be repurposed to problems involving AI models, and enumerate reasons why this is so. We introduce an alternate alignment approach informed by social science tools and characterized by three steps: 1. defining a positive desired social outcome for human/AI collaboration as the goal or "North Star," 2. properly framing knowns and unknowns, and 3. forming diverse teams to investigate, observe, and navigate emerging challenges in alignment.

Adversarial information operations can destabilize societies by undermining fair elections, manipulating public opinions on policies, and promoting scams. Despite their widespread occurrence and potential impacts, our understanding of influence campaigns is limited by manual analysis of messages and subjective interpretation of their observable behavior. In this paper, we explore whether these limitations can be mitigated with large language models (LLMs), using GPT-3.5 as a case-study for coordinated campaign annotation. We first use GPT-3.5 to scrutinize 126 identified information operations spanning over a decade. We utilize a number of metrics to quantify the close (if imperfect) agreement between LLM and ground truth descriptions. We next extract coordinated campaigns from two large multilingual datasets from X (formerly Twitter) that respectively discuss the 2022 French election and 2023 Balikaran Philippine-U.S. military exercise in 2023. For each coordinated campaign, we use GPT-3.5 to analyze posts related to a specific concern and extract goals, tactics, and narrative frames, both before and after critical events (such as the date of an election). While the GPT-3.5 sometimes disagrees with subjective interpretation, its ability to summarize and interpret demonstrates LLMs' potential to extract higher-order indicators from text to provide a more complete picture of the information campaigns compared to previous methods.

Air pollution is a significant health concern worldwide, contributing to various respiratory diseases. Advances in air quality mapping, driven by the emergence of smart cities and the proliferation of Internet-of-Things sensor devices, have led to an increase in available data, fueling momentum in air pollution forecasting. The objective of this study is to devise an integrated approach for predicting air quality using image data and subsequently assessing lung disease severity based on Air Quality Index (AQI).The aim is to implement an integrated approach by refining existing techniques to improve accuracy in predicting AQI and lung disease severity. The study aims to forecast additional atmospheric pollutants like AQI, PM10, O3, CO, SO2, NO2 in addition to PM2.5 levels. Additionally, the study aims to compare the proposed approach with existing methods to show its effectiveness. The approach used in this paper uses VGG16 model for feature extraction in images and neural network for predicting AQI.In predicting lung disease severity, Support Vector Classifier (SVC) and K-Nearest Neighbors (KNN) algorithms are utilized. The neural network model for predicting AQI achieved training accuracy of 88.54 % and testing accuracy of 87.44%,which was measured using loss function, while the KNN model used for predicting lung disease severity achieved training accuracy of 98.4% and testing accuracy of 97.5% In conclusion, the integrated approach presented in this study forecasts air quality and evaluates lung disease severity, achieving high testing accuracies of 87.44% for AQI and 97.5% for lung disease severity using neural network, KNN, and SVC models. The future scope involves implementing transfer learning and advanced deep learning modules to enhance prediction capabilities. While the current study focuses on India, the objective is to expand its scope to encompass global coverage.