We reveal the theoretical foundations of techniques for editing large language models, and present new methods which can do so without requiring retraining. Our theoretical insights show that a single metric (a measure of the intrinsic dimension of the model's features) can be used to assess a model's editability and reveals its previously unrecognised susceptibility to malicious stealth attacks. This metric is fundamental to predicting the success of a variety of editing approaches, and reveals new bridges between disparate families of editing methods. We collectively refer to these as stealth editing methods, because they directly update a model's weights to specify its response to specific known hallucinating prompts without affecting other model behaviour. By carefully applying our theoretical insights, we are able to introduce a new jet-pack network block which is optimised for highly selective model editing, uses only standard network operations, and can be inserted into existing networks.

We reveal new methods and the theoretical foundations of techniques for editing large language models. We also show how the new theory can be used to assess the editability of models and to expose their susceptibility to previously unknown malicious attacks. Our theoretical approach shows that a single metric (a specific measure of the intrinsic dimensionality of the model's features) is fundamental to predicting the success of popular editing approaches, and reveals new bridges between disparate families of editing methods. We collectively refer to these approaches as stealth editing methods, because they aim to directly and inexpensively update a model's weights to correct the model's responses to known hallucinating prompts without otherwise affecting the model's behaviour, without requiring retraining. By carefully applying the insight gleaned from our theoretical investigation, we are able to introduce a new network block -- named a jet-pack block -- which is optimised for highly selective model editing, uses only standard network operations, and can be inserted into existing networks. The intrinsic dimensionality metric also determines the vulnerability of a language model to a stealth attack: a small change to a model's weights which changes its response to a single attacker-chosen prompt. Stealth attacks do not require access to or knowledge of the model's training data, therefore representing a potent yet previously unrecognised threat to redistributed foundation models. They are computationally simple enough to be implemented in malware in many cases. Extensive experimental results illustrate and support the method and its theoretical underpinnings.

Network attacks have became increasingly more sophisticated and stealthy due to the advances in technologies and the growing sophistication of attackers. Advanced Persistent Threats (APTs) are a type of attack that implement a wide range of strategies to evade detection and be under the defence radar. Software Defined Network (SDN) is a network paradigm that implements dynamic configuration by separating the control plane from the network plane. This approach improves security aspects by facilitating the employment of network intrusion detection systems. Implementing Machine Learning (ML) techniques in Intrusion Detection Systems (IDSs) is widely used to detect such attacks but has a challenge when the data distribution changes. Concept drift is a term that describes the change in the relationship between the input data and the target value (label or class). The model is expected to degrade as certain forms of change occur. In this paper, the primary form of change will be in user behaviour (particularly changes in attacker behaviour). It is essential for a model to adapt itself to deviations in data distribution. SDN can help in monitoring changes in data distribution. This paper discusses changes in stealth attacker behaviour. The work described here investigates various concept drift detection algorithms. An incremental hybrid adaptive Network Intrusion Detection System (NIDS) is proposed to tackle the issue of concept drift in SDN. It can detect known and unknown attacks. The model is evaluated over different datasets showing promising results.

We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself. Such a stealth attack could be conducted by a mischievous, corrupt or disgruntled member of a software development team. It could also be made by those wishing to exploit a "democratization of AI" agenda, where network architectures and trained parameter sets are shared publicly. Building on work by [Tyukin et al., International Joint Conference on Neural Networks, 2020], we develop a range of new implementable attack strategies with accompanying analysis, showing that with high probability a stealth attack can be made transparent, in the sense that system performance is unchanged on a fixed validation set which is unknown to the attacker, while evoking any desired output on a trigger input of interest. The attacker only needs to have estimates of the size of the validation set and the spread of the AI's relevant latent space. In the case of deep learning neural networks, we show that a one neuron attack is possible - a modification to the weights and bias associated with a single neuron - revealing a vulnerability arising from over-parameterization. We illustrate these concepts in a realistic setting. Guided by the theory and computational results, we also propose strategies to guard against stealth attacks.

In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an input space into a decision space, including artificial neural networks used in deep learning applications. Two classes of attacks are considered. The first class involves adversarial examples and concerns the introduction of small perturbations of the input data that cause misclassification. The second class, introduced here for the first time and named stealth attacks, involves small perturbations to the AI system itself. Here the perturbed system produces whatever output is desired by the attacker on a specific small data set, perhaps even a single input, but performs as normal on a validation set (which is unknown to the attacker). We show that in both cases, i.e., in the case of an attack based on adversarial examples and in the case of a stealth attack, the dimensionality of the AI's decision-making space is a major contributor to the AI's susceptibility. For attacks based on adversarial examples, a second crucial parameter is the absence of local concentrations in the data probability distribution, a property known as Smeared Absolute Continuity. According to our findings, robustness to adversarial examples requires either (a) the data distributions in the AI's feature space to have concentrated probability density functions or (b) the dimensionality of the AI's decision variables to be sufficiently small. We also show how to construct stealth attacks on high-dimensional AI systems that are hard to spot unless the validation set is made exponentially large.

Artificial intelligence is a double-edged sword that can be used as a security solution or as a weapon by hackers. AI entails developing programs and systems capable of exhibiting traits associated with human behaviors. The characteristics include the ability to adapt to a particular environment or to intelligently respond to a situation. AI technologies have extensively been applied in cybersecurity solutions, but hackers are also leveraging them to develop intelligent malware programs and execute stealth attacks. Security experts have conducted a lot of research to harness the capabilities of AI and incorporate it into security solutions.