相关论文: Making Code Re-randomization Practical with MARDU

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Machine learning models have been widely used in security applications such as intrusion detection, spam filtering, and virus or malware detection. However, it is well-known that adversaries are always trying to adapt their attacks to evade…

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

Large language models (LLMs) have achieved remarkable progress in code generation, yet their potential for software protection remains largely untapped. Reverse engineering continues to threaten software security, while traditional virtual…

Randomizing the mapping of addresses to cache entries has proven to be an effective technique for hardening caches against contention-based attacks like Prime+Prome. While attacks and defenses are still evolving, it is clear that randomized…

Pre-trained code generation models (PCGMs) have been widely applied in neural code generation which can generate executable code from functional descriptions in natural languages, possibly together with signatures. Despite substantial…

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…

Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which…

Reversible data hiding (RDH) has been extensively studied in the field of information security. In our previous work [1], an explicit implementation approaching the rate-distortion bound of RDH has been proposed. However, there are two…

In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to…

This paper presents DAEDALUS, a software diversity-based framework designed to resist ROP attacks on Linux-based IoT devices. DAEDALUS generates unique, semantically equivalent but syntactically different rewrites of IoT firmware,…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Return Oriented programming was surfaced first a decade ago, and was built to overcome the buffer exploit defense mechanisms like ASLR, DEP (or W^ X) by method of reusing the system code in the form of gadgets which are stitched together to…

We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical…

The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…

Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations. The current most effective defense methods against these adversarial attacks are variants of adversarial training. In this paper, we introduce a…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

In this paper, we introduce a formal notion of partial compliance, called Attack-resistance, of a computer program running together with a defense mechanism w.r.t a non-exploitability specification. In our setting, a program may contain…

Control-flow attacks, usually achieved by exploiting a buffer-overflow vulnerability, have been a serious threat to system security for over fifteen years. Researchers have answered the threat with various mitigation techniques, but…