Related papers: JIT Spraying and Mitigations
Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…
Dataset distillation (DD) enhances training efficiency and reduces bandwidth by condensing large datasets into smaller synthetic ones. It enables models to achieve performance comparable to those trained on the raw full dataset and has…
We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…
The abundance of cyber-physical components in modern day power grid with their diverse hardware and software vulnerabilities has made it difficult to protect them from advanced persistent threats (APTs). An attack graph depicting the…
The development of quantum computers has been advancing rapidly in recent years. As quantum computers become more widely accessible, potentially malicious users could try to execute their code on the machines to leak information from other…
Rowhammer is a well-studied DRAM phenomenon wherein multiple activations to a given row can cause bit flips in adjacent rows. Many mitigation techniques have been introduced to address Rowhammer, with some support being incorporated into…
Gradient-based adversarial attacks on deep neural networks pose a serious threat, since they can be deployed by adding imperceptible perturbations to the test data of any network, and the risk they introduce cannot be assessed through the…
Code obfuscation is a major tool for protecting software intellectual property from attacks such as reverse engineering or code tampering. Yet, recently proposed (automated) attacks based on Dynamic Symbolic Execution (DSE) shows very…
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has emerged to synthesize a compact dataset that preserves critical…
We introduce IMPACT, a set of high-throughput main memory-based timing attacks that leverage characteristics of processing-in-memory (PiM) architectures to establish covert and side channels. IMPACT enables high-throughput communication and…
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility…
This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel…
Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…
As the complexities of Dynamic Data Driven Applications Systems increase, preserving their resilience becomes more challenging. For instance, maintaining power grid resilience is becoming increasingly complicated due to the growing number…
Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety…
Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…
Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior. In this paper, we propose Constrained…
Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…
Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…
Sensitive information is present on our phones, disks, watches and computers. Its protection is essential. Plausible deniability of stored data allows individuals to deny that their device contains a piece of sensitive information. This…