Related papers: CRaFT: Circuit-Guided Refusal Feature Selection vi…
Predicting the motion of surrounding vehicles is essential for autonomous vehicles, as it governs their own motion plan. Current state-of-the-art vehicle prediction models heavily rely on map information. In reality, however, this…
Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to limited training…
Conditional Random Fields (CRFs) are undirected graphical models, a special case of which correspond to conditionally-trained finite state machines. A key advantage of these models is their great flexibility to include a wide array of…
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and…
The rapid advancement of large language models (LLMs) has brought significant benefits to various domains while introducing substantial risks. Despite being fine-tuned through reinforcement learning, LLMs lack the capability to discern…
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…
Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets. However, scaling SFT data alone is inefficient and…
Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations in LM…
Due to the increasing sophistication of web attacks, Web Application Firewalls (WAFs) have to be tested and updated regularly to resist the relentless flow of web attacks. In practice, using a brute-force attack to discover vulnerabilities…
Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make the task of crack segmentation extremely challenging. In…
Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more…
Feature selection has been an essential step in developing industry-scale deep Click-Through Rate (CTR) prediction systems. The goal of neural feature selection (NFS) is to choose a relatively small subset of features with the best…
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…
We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with complementary but incomplete views must coordinate through…
We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer…
Large language models (LLMs) have exhibited remarkable fluency across various tasks. However, their unethical applications, such as disseminating disinformation, have become a growing concern. Although recent works have proposed a number of…
High quality object proposals are crucial in visual tracking algorithms that utilize region proposal network (RPN). Refinement of these proposals, typically by box regression and classification in parallel, has been popularly adopted to…
The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single…
Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…
This paper presents an underlying framework for both automating and accelerating malware classification, more specifically, mapping malicious executables to known Advanced Persistent Threat (APT) groups. The main feature of this analysis is…