--State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. T o protect against this scenario, Adversarial Training (A T) and Adversarial Distillation (AD) include adversarial examples during the training phase, and Adversarial Purification uses a generative model to reconstruct all the images given to the classifier . This paper considers an even more realistic evaluation scenario: gray-box attacks, which assume that the attacker knows the architecture and the dataset used to train the target network, but cannot access its gradients. We provide empirical evidence that models are vulnerable to gray-box attacks and propose LISArD, a defense mechanism that does not increase computational and temporal costs but provides robustness against gray-box and white-box attacks without including A T . Our method approximates a cross-correlation matrix, created with the embeddings of perturbed and clean images, to a diagonal matrix while simultaneously conducting classification learning. Our results show that LISArD can effectively protect against gray-box attacks, can be used in multiple architectures, and carries over its resilience to the white-box scenario. Also, state-of-the-art AD models underperform greatly when removing A T and/or moving to gray-box settings, highlighting the lack of robustness from existing approaches to perform in various conditions (aside from white-box settings). EEP Neural Networks (DNNs) have achieved remarkable performance in multiple areas, such as Medical Imaging [1], [2], Natural Language Processing [3], [4], and Active Speaker Detection [5]-[7]. This accomplishment led to the wide adoption of Artificial Intelligence in the daily lives of many people, either in work or leisure scenarios, increasing the attractiveness and susceptibility of DNNs to attackers. The study of DNN security is still in its early stages.

Are LLMs Ready for Practical Adoption for Assertion Generation? Abstract --Assertions have been the de facto collateral for simulation-based and formal verification of hardware designs for over a decade. The quality of hardware verification, i.e., detection and diagnosis of corner-case design bugs, is critically dependent on the quality of the assertions. With the onset of generative AI such as Transformers and Large-Language Models (LLMs), there has been a renewed interest in developing novel, effective, and scalable techniques of generating functional and security assertions from design source code. While there have been recent works that use commercial-of-the-shelf (COTS) LLMs for assertion generation, there is no comprehensive study in quantifying the effectiveness of LLMs in generating syntactically and semantically correct assertions. In this paper, we first discuss AssertionBench from our prior work, a comprehensive set of designs and assertions to quantify the goodness of a broad spectrum of COTS LLMs for the task of assertion generations from hardware design source code. Our key insight was that COTS LLMs are not yet ready for prime-time adoption for assertion generation as they generate a considerable fraction of syntactically and semantically incorrect assertions. Motivated by the insight, we propose AssertionLLM, a first of its kind LLM model, specifically fine-tuned for assertion generation. Our initial experimental results show that AssertionLLM considerably improves the semantic and syntactic correctness of the generated assertions over COTS LLMs.

Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. However, many real-world applications-such as psychiatric diagnosis, consulting, and interviews-require AI to take a proactive role, asking the right questions and steering conversations toward specific objectives. Using mental health differential diagnosis as an application context, we introduce ProAI, a goal-oriented, proactive conversational AI framework. ProAI integrates structured knowledge-guided memory, multi-agent proactive reasoning, and a multi-faceted evaluation strategy, enabling LLMs to engage in clinician-style diagnostic reasoning rather than simple response generation. Through simulated patient interactions, user experience assessment, and professional clinical validation, we demonstrate that ProAI achieves up to 83.3% accuracy in mental disorder differential diagnosis while maintaining professional and empathetic interaction standards. These results highlight the potential for more reliable, adaptive, and goal-driven AI diagnostic assistants, advancing LLMs beyond reactive dialogue systems.

Large language models (LLMs) can exhibit advanced reasoning yet still generate incorrect answers. We hypothesize that such errors frequently stem from spurious beliefs, propositions the model internally considers true but are incorrect. To address this, we propose a method to rectify the belief space by suppressing these spurious beliefs while simultaneously enhancing true ones, thereby enabling more reliable inferences. Our approach first identifies the beliefs that lead to incorrect or correct answers by prompting the model to generate textual explanations, using our Forward-Backward Beam Search (FBBS). We then apply unlearning to suppress the identified spurious beliefs and enhance the true ones, effectively rectifying the model's belief space. Empirical results on multiple QA datasets and LLMs show that our method corrects previously misanswered questions without harming overall model performance. Furthermore, our approach yields improved generalization on unseen data, suggesting that rectifying a model's belief space is a promising direction for mitigating errors and enhancing overall reliability.

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI models to access and interpret a user's private data (e.g., conversation history, user-AI interactions, app usage) to understand personal details such as biographical information, preferences, and social connections. However, due to the sensitive nature of such data, there are no publicly available datasets that allow us to assess an AI model's ability to understand users through direct access to personal information. To address this gap, we introduce a synthetic data generation pipeline that creates diverse, realistic user profiles and private documents simulating human activities. Leveraging this synthetic data, we present PersonaBench, a benchmark designed to evaluate AI models' performance in understanding personal information derived from simulated private user data. We evaluate Retrieval-Augmented Generation (RAG) pipelines using questions directly related to a user's personal information, supported by the relevant private documents provided to the models. Our results reveal that current retrieval-augmented AI models struggle to answer private questions by extracting personal information from user documents, highlighting the need for improved methodologies to enhance personalization capabilities in AI.

Large language models (LLMs) have recently demonstrated remarkable advancements in embodying diverse personas, enhancing their effectiveness as conversational agents and virtual assistants. Consequently, LLMs have made significant strides in processing and integrating multimodal information. However, even though human personas can be expressed in both text and image, the extent to which the modality of a persona impacts the embodiment by the LLM remains largely unexplored. In this paper, we investigate how do different modalities influence the expressiveness of personas in multimodal LLMs. To this end, we create a novel modality-parallel dataset of 40 diverse personas varying in age, gender, occupation, and location. This consists of four modalities to equivalently represent a persona: image-only, text-only, a combination of image and small text, and typographical images, where text is visually stylized to convey persona-related attributes. We then create a systematic evaluation framework with 60 questions and corresponding metrics to assess how well LLMs embody each persona across its attributes and scenarios. Comprehensive experiments on $5$ multimodal LLMs show that personas represented by detailed text show more linguistic habits, while typographical images often show more consistency with the persona. Our results reveal that LLMs often overlook persona-specific details conveyed through images, highlighting underlying limitations and paving the way for future research to bridge this gap. We release the data and code at https://github.com/claws-lab/persona-modality .

Recent benchmark studies have claimed that AI has approached or even surpassed human-level performances on various cognitive tasks. However, this position paper argues that current AI evaluation paradigms are insufficient for assessing human-like cognitive capabilities. We identify a set of key shortcomings: a lack of human-validated labels, inadequate representation of human response variability and uncertainty, and reliance on simplified and ecologically-invalid tasks. We support our claims by conducting a human evaluation study on ten existing AI benchmarks, suggesting significant biases and flaws in task and label designs. To address these limitations, we propose five concrete recommendations for developing future benchmarks that will enable more rigorous and meaningful evaluations of human-like cognitive capacities in AI with various implications for such AI applications.

Large language models (LLMs) excel in tasks that require complex linguistic abilities, such as reference disambiguation and metaphor recognition/generation. Although LLMs possess impressive capabilities, their internal mechanisms for processing and representing linguistic knowledge remain largely opaque. Previous work on linguistic mechanisms has been limited by coarse granularity, insufficient causal analysis, and a narrow focus. In this study, we present a systematic and comprehensive causal investigation using sparse auto-encoders (SAEs). We extract a wide range of linguistic features from six dimensions: phonetics, phonology, morphology, syntax, semantics, and pragmatics. We extract, evaluate, and intervene on these features by constructing minimal contrast datasets and counterfactual sentence datasets. We introduce two indices-Feature Representation Confidence (FRC) and Feature Intervention Confidence (FIC)-to measure the ability of linguistic features to capture and control linguistic phenomena. Our results reveal inherent representations of linguistic knowledge in LLMs and demonstrate the potential for controlling model outputs. This work provides strong evidence that LLMs possess genuine linguistic knowledge and lays the foundation for more interpretable and controllable language modeling in future research.

The speech echo, in particular, is a specific overlapping phenomenon generated by the A TC communication between the sent and received A TCO speech. Another component of noise, radio transmission noise, is the result of A TC being transmitted over High Frequency (HF), V ery High Frequency (VHF) or Ultra High Frequency (UHF) bandwidths that are susceptible to noise caused by static, radio frequency interference, or thermal noise [38]. Auditory information is encoded using amplitude modulation (AM) because it is less susceptible to the capture effect than frequency modulation (FM) [40]. However, AM signals are also less robust against noise and interference, which has been shown to degrade the performance of ASR models [41]. Due to the complex amalgamation of noises, A TC speech often sounds muffled and unintelligible with a low signal-to-noise ratio (SNR). This poses a problem to ASR systems as the noise will either have to be learned by the ASR model or removed through de-noising measures in pre-processing. However, studies have also shown that the use of de-noisers and enhancers could potentially also result in degraded performance in ASR models, making ASR transcription a tricky problem to address [25].

Automated machine learning (AutoML) is a research area focusing on using optimisation techniques to design machine learning (ML) algorithms, alleviating the need for a human to perform manual algorithm design. Real-time AutoML enables the design process to happen while the ML algorithm is being applied to a task. Real-time AutoML is an emerging research area, as such existing real-time AutoML techniques need improvement with respect to the quality of designs and time taken to create designs. To address these issues, this study proposes an Online Meta-learning for AutoML in Real-time (OnMAR) approach. Meta-learning gathers information about the optimisation process undertaken by the ML algorithm in the form of meta-features. Meta-features are used in conjunction with a meta-learner to optimise the optimisation process. The OnMAR approach uses a meta-learner to predict the accuracy of an ML design. If the accuracy predicted by the meta-learner is sufficient, the design is used, and if the predicted accuracy is low, an optimisation technique creates a new design. A genetic algorithm (GA) is the optimisation technique used as part of the OnMAR approach. Different meta-learners (k-nearest neighbours, random forest and XGBoost) are tested. The OnMAR approach is model-agnostic (i.e. not specific to a single real-time AutoML application) and therefore evaluated on three different real-time AutoML applications, namely: composing an image clustering algorithm, configuring the hyper-parameters of a convolutional neural network, and configuring a video classification pipeline. The OnMAR approach is effective, matching or outperforming existing real-time AutoML approaches, with the added benefit of a faster runtime.