Related papers: You Cannot Always Win the Race: Analyzing the LFEN…

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Autonomous agentic AI systems powered by vision-language models (VLMs) are rapidly advancing toward real-world deployment, yet their cross-modal reasoning capabilities introduce new attack surfaces for adversarial manipulation that exploit…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

LLMs are increasingly used world-wide from daily tasks to agentic systems and data analytics, requiring significant GPU resources. LLM inference systems, however, are slow compared to database systems, and inference performance and…

Federated Learning (FL) is a collaborative machine learning approach allowing participants to jointly train a model without having to share their private, potentially sensitive local datasets with others. Despite its benefits, FL is…

The proliferation and application of machine learning based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the…

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…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive…

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

The IP-stride prefetcher has recently been exploited to leak secrets through side-channel attacks. It, however, cannot be simply disabled for security with prefetching speedup as a sacrifice. The state-of-the-art defense tries to retain the…

Toward robust malware detection, we explore the attack surface of existing malware detection systems. We conduct root-cause analyses of the practical binary-level black-box adversarial malware examples. Additionally, we uncover the…

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing…

As technology continues to advance and we usher in the era of Industry 5.0, there has been a profound paradigm shift in operating systems, file systems, web, and network applications. The conventional utilization of multiprocessing and…

One of the most prevalent source of side channel vulnerabilities is the secret-dependent behavior of conditional branches (SDBCB). The state-of-the-art solution relies on Constant-Time Expressions, which require high programming effort and…

LLMs demonstrate strong performance on code benchmarks, yet consistent reasoning across forward and backward execution remains elusive. We present RoundTripCodeEval (RTCE), a benchmark of four code execution reasoning tasks that evaluates…

State of the art deep learning techniques are known to be vulnerable to evasion attacks where an adversarial sample is generated from a malign sample and misclassified as benign. Detection of encrypted malware command and control traffic…

Modern AI inference systems treat transformer execution as mandatory, conflating model capability with execution necessity. We reframe inference as a control-plane decision problem: determining when execution is necessary versus when…