相关论文: Attention Shift: Steering AI Away from Unsafe Cont…
As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on post-hoc mitigation -- especially machine unlearning and inference-time guardrails -- to argue for compliance. This paper argues…
Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety. Machine unlearning seeks to remove the influence of a targeted forget set while preserving model…
In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…
Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)'s…
Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…
Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…
Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…
By and large, the professional handling of huge data collections is regarded as a fundamental ingredient of the progress of machine learning and of its spectacular results in related disciplines, with a growing agreement on risks connected…
Generative AI systems may pose serious risks to individuals vulnerable to eating disorders. Existing safeguards tend to overlook subtle but clinically significant cues, leaving many risks unaddressed. To better understand the nature of…
Generative artificial intelligence revolutionized society. Current models are trained by minimizing the distance between the produced data and the training set. Consequently, development is plateauing as they are intrinsically data-hungry…
When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase…
The groundbreaking advancements around generative AI have recently caused a wave of concern culminating in a row of lawsuits, including high-profile actions against Stability AI and OpenAI. This situation of legal uncertainty has sparked a…
As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…
Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By…
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…
We propose an attention-based networks for transferring motions between arbitrary objects. Given a source image(s) and a driving video, our networks animate the subject in the source images according to the motion in the driving video. In…
Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by…
In the age of powerful AI-generated text, automatic detectors have emerged to identify machine-written content. This poses a threat to author privacy and freedom, as text authored with AI assistance may be unfairly flagged. We propose…