Related papers: Adversaries Can Misuse Combinations of Safe Models

Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer across models. We hypothesize that adversarial weakness is…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for…

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to…

AI systems have the potential to improve decision-making, but decision makers face the risk that the AI may be misaligned with their objectives. We study this problem in the context of a treatment decision, where a designer decides which…

Most machine learning models are validated and tested on fixed datasets. This can give an incomplete picture of the capabilities and weaknesses of the model. Such weaknesses can be revealed at test time in the real world. The risks involved…

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

Recent large-scale events like election fraud and financial scams have shown how harmful coordinated efforts by human groups can be. With the rise of autonomous AI systems, there is growing concern that AI-driven groups could also cause…

Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify risks before deployment. However, it has been recognised that if AI agents are aware that…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Machine learning techniques are immensely deployed in both industry and academy. Recent studies indicate that machine learning models used for classification tasks are vulnerable to adversarial examples, which limits the usage of…

Regulation, legal liabilities, and societal concerns challenge the adoption of AI in safety and security-critical applications. One of the key concerns is that adversaries can cause harm by manipulating model predictions without being…

Pseudo healthy synthesis, i.e. the creation of a subject-specific `healthy' image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data…

A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or other attacks. At least two methods can identify foundation…

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…

Answering complex questions often requires multi-step reasoning in order to obtain the final answer. Most research into decompositions of complex questions involves open-domain systems, which have shown success in using these decompositions…

Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans.…

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…