HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment

With the introduction of the transformers architecture, LLMs have revolutionized the NLP field with ever more powerful models. Nevertheless, their development came up with several challenges. The exponential growth in computational power and reasoning capabilities of language models has heightened concerns about their security. As models become more powerful, ensuring their safety has become a crucial focus in research. This paper aims to address gaps in the current literature on jailbreaking techniques and the evaluation of LLM vulnerabilities. Our contributions include the creation of a novel dataset designed to assess the harmfulness of model outputs across multiple harm levels, as well as a focus on fine-grained harm-level analysis. Using this framework, we provide a comprehensive benchmark of state-of-the-art jailbreaking attacks, specifically targeting the Vicuna 13B v1.5 model. Additionally, we examine how quantization techniques, such as AWQ and GPTQ, influence the alignment and robustness of models, revealing trade-offs between enhanced robustness with regards to transfer attacks and potential increases in vulnerability on direct ones. This study aims to demonstrate the influence of harmful input queries on the complexity of jailbreaking techniques, as well as to deepen our understanding of LLM vulnerabilities and improve methods for assessing model robustness when confronted with harmful content, particularly in the context of compression strategies.

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual defenses, but in practice, models may undergo simultaneous attacks. This study explores the combination of adversarial training and differentially private training to defend against simultaneous attacks. While differentially-private adversarial training, as presented in DP-Adv, outperforms the other state-of-the-art methods in performance, it lacks formal privacy guarantees and empirical validation. Thus, in this work, we benchmark the performance of this technique using a membership inference attack and empirically show that the resulting approach is as private as non-robust private models. This work also highlights the need to explore privacy guarantees in dynamic training paradigms.

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience

Machine learning models are being used in an increasing number of critical applications; thus, securing their integrity and ownership is critical. Recent studies observed that adversarial training and watermarking have a conflicting interaction. This work introduces a novel framework to integrate adversarial training with watermarking techniques to fortify against evasion attacks and provide confident model verification in case of intellectual property theft. We use adversarial training together with adversarial watermarks to train a robust watermarked model. The key intuition is to use a higher perturbation budget to generate adversarial watermarks compared to the budget used for adversarial training, thus avoiding conflict. We use the MNIST and Fashion-MNIST datasets to evaluate our proposed technique on various model stealing attacks. The results obtained consistently outperform the existing baseline in terms of robustness performance and further prove the resilience of this defense against pruning and fine-tuning removal attacks.

VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection

This paper presents VulBERTa, a deep learning approach to detect security vulnerabilities in source code. Our approach pre-trains a RoBERTa model with a custom tokenisation pipeline on real-world code from open-source C/C++ projects. The model learns a deep knowledge representation of the code syntax and semantics, which we leverage to train vulnerability detection classifiers. We evaluate our approach on binary and multi-class vulnerability detection tasks across several datasets (Vuldeepecker, Draper, REVEAL and muVuldeepecker) and benchmarks (CodeXGLUE and D2A). The evaluation results show that VulBERTa achieves state-of-the-art performance and outperforms existing approaches across different datasets, despite its conceptual simplicity, and limited cost in terms of size of training data and number of model parameters.

Certified Federated Adversarial Training

In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on certain numbers of benign clients being present in a quorum of workers. This can be hard to guarantee when clients can join at will, or join based on factors such as idle system status, and connected to power and WiFi. We tackle the scenario of securing FL systems conducting adversarial training when a quorum of workers could be completely malicious. We model an attacker who poisons the model to insert a weakness into the adversarial training such that the model displays apparent adversarial robustness, while the attacker can exploit the inserted weakness to bypass the adversarial training and force the model to misclassify adversarial examples. We use abstract interpretation techniques to detect such stealthy attacks and block the corrupted model updates. We show that this defence can preserve adversarial robustness even against an adaptive attacker.

A Hybrid Graph Neural Network Approach for Detecting PHP Vulnerabilities

This paper presents DeepTective, a deep learning approach to detect vulnerabilities in PHP source code. Our approach implements a novel hybrid technique that combines Gated Recurrent Units and Graph Convolutional Networks to detect SQLi, XSS and OSCI vulnerabilities leveraging both syntactic and semantic information. We evaluate DeepTective and compare it to the state of the art on an established synthetic dataset and on a novel real-world dataset collected from GitHub. Experimental results show that DeepTective achieves near perfect classification on the synthetic dataset, and an F1 score of 88.12% on the realistic dataset, outperforming related approaches. We validate DeepTective in the wild by discovering 4 novel vulnerabilities in established WordPress plugins.

Intrusion Detection for Industrial Control Systems: Evaluation Analysis and Adversarial Attacks

Neural networks are increasingly used in security applications for intrusion detection on industrial control systems. In this work we examine two areas that must be considered for their effective use. Firstly, is their vulnerability to adversarial attacks when used in a time series setting. Secondly, is potential over-estimation of performance arising from data leakage artefacts. To investigate these areas we implement a long short-term memory (LSTM) based intrusion detection system (IDS) which effectively detects cyber-physical attacks on a water treatment testbed representing a strong baseline IDS. For investigating adversarial attacks we model two different white box attackers. The first attacker is able to manipulate sensor readings on a subset of the Secure Water Treatment (SWaT) system. By creating a stream of adversarial data the attacker is able to hide the cyber-physical attacks from the IDS. For the cyber-physical attacks which are detected by the IDS, the attacker required on average 2.48 out of 12 total sensors to be compromised for the cyber-physical attacks to be hidden from the IDS. The second attacker model we explore is an $L_{\infty}$ bounded attacker who can send fake readings to the IDS, but to remain imperceptible, limits their perturbations to the smallest $L_{\infty}$ value needed. Additionally, we examine data leakage problems arising from tuning for $F_1$ score on the whole SWaT attack set and propose a method to tune detection parameters that does not utilise any attack data. If attack after-effects are accounted for then our new parameter tuning method achieved an $F_1$ score of 0.811$\pm$0.0103.

Deep Latent Defence

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to cause misclassification. The level of perturbation an attacker needs to introduce in order to cause such a misclassification can be extremely small, and often imperceptible. This is of significant security concern, particularly where misclassification can cause harm to humans. We thus propose Deep Latent Defence, an architecture which seeks to combine adversarial training with a detection system. At its core Deep Latent Defence has a adversarially trained neural network. A series of encoders take the intermediate layer representation of data as it passes though the network and project it to a latent space which we use for detecting adversarial samples via a $k$-nn classifier. We present results using both grey and white box attackers, as well as an adaptive $L_{\infty}$ bounded attack which was constructed specifically to try and evade our defence. We find that even under the strongest attacker model that we have investigated our defence is able to offer significant defensive benefits.