We construct a class of locally differentially private mechanisms for linear queries, including range queries, representable as a multiplicative operation of a pre-specified workload matrix and a confidential database. The proposed design leverages correlated input perturbation to simultaneously satisfy the following crucial properties: Unbiasedness: The sanitized output exhibits no bias with respect to the ground truth; Consistency (internal): The sanitized output may plausibly be viewed as having been queried directly from an input database without modification; Statistical transparency: The probabilistic description of the sanitized output is analytically tractable to enable reliable downstream statistical inferences; Utility control: The mechanism accommodates custom, externally specified utility requirements, expressed in terms of accuracy targets in certain query margins or as implied by the hierarchical database structure; Efficient implementation: The proposed algorithm is exact and simple to implement, with no need for approximate simulation (including Markov chain Monte Carlo) nor optimization-based post-processing. The curation of official statistics vividly illustrates the need and the challenge to simultaneously satisfy the above desiderata. As an example, the 2020 U.S. Decennial Census provide multi-resolutional tabular data products that follow a hierarchical system termed the "spine" Abowd et al. (2022), which orders from top to bottom geographic entities (states, counties, tracts, block groups, and blocks), with higher-level geographies partitioned by the lower-level ones. Population tabulations across the geographic resolutions are subject to numerous complex utility requirements. For example, state-level populations must be exactly reported per their constitutional purpose for reapportionment - an "invariant" requirement akin to external consistency; see Gao et al. (2022); Dharangutte et al. (2023). Tabulations at intermediate geographies must meet accuracy targets according to the relevant operational standards U.S. Census Bureau (2022), as does certain "off-spine" geographies (e.g.

Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA), from demonstrations. Unfortunately, these techniques are generally not sample efficient. In this work, we introduce $L^*LM$, an algorithm for learning DFAs from both demonstrations and natural language. Due to the expressivity of natural language, we observe a significant improvement in the data efficiency of learning DFAs from expert demonstrations. Technically, $L^*LM$ leverages large language models to answer membership queries about the underlying task. This is then combined with recent techniques for transforming learning from demonstrations into a sequence of labeled example learning problems. In our experiments, we observe the two modalities complement each other, yielding a powerful few-shot learner.

This legal action ignited a heated debate, contributing to a growing series of lawsuits against AI providers [9-11, 54]. This incident underscores the inadequacy of current AI harm reporting mechanisms, leaving small harmed parties with limited recourse unless backed by substantial legal support or media awareness, despite the recognized potential for improving AI systems by exposing issues [78]. Current AI accountability initiatives primarily rely on periodic audits, emphasizing repetitive assessments but lacking a structured reporting framework for user-identified issues post-deployment. This audit-centric paradigm is reflected in influential policies such as the U.S. Executive Order on AI [93], the EU's draft AI Act [43], and New York City's Local Law 144[69]. However, this approach falls short when compared to the more comprehensive Coordinated Vulnerability Disclosure(CVD) processes standard in software security. Coordinated Vulnerability Disclosure (CVD) plays a crucial role as a mechanism for independent researchers to report newly identified vulnerabilities to affected vendors and the public [58]. This process enables transparent remediation before potential exploitation by malicious actors and has become a vital practice enshrined in government regulations and industry standards. Notably, the FDA mandates the implementation of CVD programs for medical device companies to enhance cybersecurity[96]. While CVD has demonstrated effectiveness in traditional software security, its direct application to machine learning (ML) systems faces unique challenges.

In the rapidly evolving field of text generation, the demand for more precise control mechanisms has become increasingly apparent. To address this need, we present a novel methodology, LIFI, which offers a lightweight approach with fine-grained control for controlled text generation. Unlike previous studies that train pre-trained language models to follow discrete, categorical, and exclusive control codes, LIFI learns controlled text generation under the guidance of continuous, relative, and nonexclusive control codes. These fine-grained codes are automatically derived from an attribute classifier, initially trained with a small amount of labeled data and subsequently employed to label abundant unlabeled data, thus garnering more extensive supervision signals. Moreover, to achieve efficient control, we incorporate the fine-grained control codes with adapters, a parameter- and compute-efficient way to steer a pre-trained language model. We evaluate LIFI on two conventional tasks -- sentiment control and topic control -- and one newly proposed task -- stylistic novel writing. Comprehensive experimental results validate the effectiveness of our proposed methods, demonstrating substantial performance improvements over existing baselines.

Large Language Models (LLMs) are increasingly integrated with external tools. While these integrations can significantly improve the functionality of LLMs, they also create a new attack surface where confidential data may be disclosed between different components. Specifically, malicious tools can exploit vulnerabilities in the LLM itself to manipulate the model and compromise the data of other services, raising the question of how private data can be protected in the context of LLM integrations. In this work, we provide a systematic way of evaluating confidentiality in LLM-integrated systems. For this, we formalize a "secret key" game that can capture the ability of a model to conceal private information. This enables us to compare the vulnerability of a model against confidentiality attacks and also the effectiveness of different defense strategies. In this framework, we evaluate eight previously published attacks and four defenses. We find that current defenses lack generalization across attack strategies. Building on this analysis, we propose a method for robustness fine-tuning, inspired by adversarial training. This approach is effective in lowering the success rate of attackers and in improving the system's resilience against unknown attacks.

Large language models (LLMs) powered conversational search systems have already been used by hundreds of millions of people, and are believed to bring many benefits over conventional search. However, while decades of research and public discourse interrogated the risk of search systems in increasing selective exposure and creating echo chambers -- limiting exposure to diverse opinions and leading to opinion polarization, little is known about such a risk of LLM-powered conversational search. We conduct two experiments to investigate: 1) whether and how LLM-powered conversational search increases selective exposure compared to conventional search; 2) whether and how LLMs with opinion biases that either reinforce or challenge the user's view change the effect. Overall, we found that participants engaged in more biased information querying with LLM-powered conversational search, and an opinionated LLM reinforcing their views exacerbated this bias. These results present critical implications for the development of LLMs and conversational search systems, and the policy governing these technologies.

Pseudo-Random Number Generators (PRNGs) have become ubiquitous in machine learning technologies because they are interesting for numerous methods. The field of machine learning holds the potential for substantial advancements across various domains, as exemplified by recent breakthroughs in Large Language Models (LLMs). However, despite the growing interest, persistent concerns include issues related to reproducibility and energy consumption. Reproducibility is crucial for robust scientific inquiry and explainability, while energy efficiency underscores the imperative to conserve finite global resources. This study delves into the investigation of whether the leading Pseudo-Random Number Generators (PRNGs) employed in machine learning languages, libraries, and frameworks uphold statistical quality and numerical reproducibility when compared to the original C implementation of the respective PRNG algorithms. Additionally, we aim to evaluate the time efficiency and energy consumption of various implementations. Our experiments encompass Python, NumPy, TensorFlow, and PyTorch, utilizing the Mersenne Twister, PCG, and Philox algorithms. Remarkably, we verified that the temporal performance of machine learning technologies closely aligns with that of C-based implementations, with instances of achieving even superior performances. On the other hand, it is noteworthy that ML technologies consumed only 10% more energy than their C-implementation counterparts. However, while statistical quality was found to be comparable, achieving numerical reproducibility across different platforms for identical seeds and algorithms was not achieved.

Researchers have slammed US officials for not rolling out stricter AI rules before popstar Taylor Swift became victim of deepfakes. Images showing the four-time Grammy winner in a series of sexual acts while dressed in Kansas City Chief memorabilia and in the stadium - and the pornography share - was viewed 47 million times online before being removed. A professor at George Washington University Law School said if proper legislation was'passed years ago' Swift and others would not have experienced such abuse. 'We are too little, too late at this point,' said Mary Anne Franks. 'It's not just going to be the 14-year-old girl or Taylor Swift. It's going to be politicians.

The UK's new artificial intelligence safety body has found that the technology can deceive human users, produce biased outcomes and has inadequate safeguards against giving out harmful information. The AI Safety Institute published initial findings from its research into advanced AI systems known as large language models (LLMs), which underpin tools such as chatbots and image generators, and found a number of concerns. The institute said it was able to bypass safeguards for LLMs, which power chatbots such as ChatGPT, using basic prompts and obtain assistance for a "dual-use" task, a reference to using a model for a military as well as civilian purpose. "Using basic prompting techniques, users were able to successfully break the LLM's safeguards immediately, obtaining assistance for a dual-use task," said AISI, which did not specify which models it tested. "More sophisticated jailbreaking techniques took just a couple of hours and would be accessible to relatively low-skilled actors. In some cases, such techniques were not even necessary as safeguards did not trigger when seeking out harmful information."

Fox News national security correspondent Jennifer Griffin has new details on the U.S. drone strike killing a Kataib Hezbollah commander on'Special Report.' Swiss police say a 32-year-old Iranian asylum-seeker was killed by police after he used an axe and a knife to seize more than a dozen hostages for several hours on a train in western Switzerland. The man took the hostages early Thursday evening and police, alerted by passengers, sealed off the area while the train was stopped in the town of Essert-sous-Champvert, police in the French-speaking Vaud region said Friday. The man, speaking Farsi and English, demanded that the train engineer join the 15 hostages. Nearly four hours after the incident began, police stormed the train after trying to negotiate with the man through an interpreter.