Related papers: CRaFT: Circuit-Guided Refusal Feature Selection vi…

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally…

Selecting a small, high-quality subset from a large corpus for fine-tuning is increasingly important as corpora grow to tens of millions of datapoints, making full fine-tuning expensive and often unnecessary. We propose CRAFT (Clustered…

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Click-Through Rate (CTR) prediction is a core task in nowadays commercial recommender systems. Feature crossing, as the mainline of research on CTR prediction, has shown a promising way to enhance predictive performance. Even though various…

LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth…

Jailbreaking in Large Language Models (LLMs) threatens their safe use in sensitive domains like education by allowing users to bypass ethical safeguards. This study focuses on detecting jailbreaks in 2-Sigma, a clinical education platform…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabilities, behavioral profile, and internal failure mode. We study behavioral and mechanistic…

This paper introduces KRATT, a removal and structural analysis attack against state-of-the-art logic locking techniques, such as single and double flip locking techniques (SFLTs and DFLTs). KRATT utilizes powerful quantified Boolean…

LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…

Reinforcement learning (RL) enables robots to operate in uncertain environments, but standard approaches often struggle with poor generalization to unseen tasks. Context-adaptive meta reinforcement learning addresses these limitations by…

Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initializing attacks via self-transfer from other prompts…

Activation functions can have a significant impact on reducing the topological complexity of input data and therefore improve the performance of the model. Selecting a suitable activation function is an essential step in neural model…

Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions…

We present Consistent-Recurrent Feature Flow Transformer (CRFT), a unified coarse-to-fine framework based on feature flow learning for robust cross-modal image registration. CRFT learns a modality-independent feature flow representation…

Click-through prediction (CTR) models transform features into latent vectors and enumerate possible feature interactions to improve performance based on the input feature set. Therefore, when selecting an optimal feature set, we should…

Mechanistic interpretability aims to reverse-engineer transformer computations by identifying causal circuits through activation patching. However, scaling these interventions across diverse prompts and task families produces…

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level,…

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppressing isolated neurons or features. However, harmful…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…