26 matches found
DVDR_LLM
DVDR-LLM: When Are LLMs Better Together for Software Vulnerability Detection and Repair? Official implementation and artifact for the research paper: "DVDR-LLM: When Are LLMs Better Together for Software Vulnerability Detection and Repair?" 🎯 Overview DVDR-LLM is an ensemble framework that...
Compressed Oracle Duality: A Simple Framework for Knowing What Quantum Adversaries Know
Given a quantum adversary that queries a random oracle, how do we characterize the information that they "know"? The Compressed Oracle method of Zhandry CRYPTO 2019 is one method that records the queries that the adversary makes; this recording serves as a representation of the information that i...
Exploring the Empirical Privacy Landscape of Synthetic Data
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a controlled comparison of data-level and training-level interventions for navigating the capability-privacy tradeoff on...
The Right to Be Forgotten under Correlation: Privacy-Utility Tradeoffs
We study privacy-preserving algorithms that redact information from a correlated dataset. The goal is to reduce the information leakage about sensitive parts. We analytically characterize the optimal tradeoff between privacy leakage through correlation and utility number of redactions for local...
Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks MIAs significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial Training, and undefended models all leak traini...
When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs
Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...
Twin Agent: Context Residual Compression for Privilege Separated Agents
Large language model LLM agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and...
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work:...
Incremental Federated Learning for Intrusion Detection in IoT Networks under Evolving Threat Landscape
The expansion of Internet of Things IoT devices has increased the attack surface of networks, necessitating a robust and adaptive intrusion detection systems. Machine learning based systems have been considered promising in enhancing the detection performance. Federated learning settings enabled ...
Exploring the Integration of Differential Privacy in Cybersecurity Analytics: Balancing Data Utility and Privacy in Threat Intelligence
To resolve the acute problem of privacy protection and guarantee that data can be used in the context of threat intelligence, this paper considers the implementation of Differential Privacy DP in cybersecurity analytics. DP, which is a sound mathematical framework, ensures privacy by adding a...
Sensing Security in Near-Field ISAC: Exploiting Scatterers for Eavesdropper Deception
In this paper, we explore sensing security in near-field NF integrated sensing and communication ISAC scenarios by exploiting known scatterers in the sensing scene. We propose a location deception LD scheme where scatterers are deliberately illuminated with probing power that is higher than that...
Learning-Based Privacy-Preserving Graph Publishing against Sensitive Link Inference Attacks
Publishing graph data is widely desired to enable a variety of structural analyses and downstream tasks. However, it also potentially poses severe privacy leakage, as attackers may leverage the released graph data to launch attacks and precisely infer private information such as the existence of...
UniAud: a Unified Auditing Framework for High Auditing Power and Utility with One Training Run
Differentially private DP optimization has been widely adopted as a standard approach to provide rigorous privacy guarantees for training datasets. DP auditing verifies whether a model trained with DP optimization satisfies its claimed privacy level by estimating empirical privacy lower bounds...
Efficient Blockchain-Based Steganography Via Backcalculating Generative Adversarial Network
Blockchain-based steganography enables data hiding via encoding the covert data into a specific blockchain transaction field. However, previous works focus on the specific field-embedding methods while lacking a consideration on required field-generation embedding. In this paper, we propose a...
CSVAR: Enhancing Visual Privacy in Federated Learning Via Adaptive Shuffling against Overfitting
Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to...
DynaNoise: Dynamic Probabilistic Noise Injection for Defending against Membership Inference Attacks
Membership Inference Attacks MIAs pose a significant risk to the privacy of training datasets by exploiting subtle differences in model outputs to determine whether a particular data sample was used during training. These attacks can compromise sensitive information, especially in domains such as...
Privacy and Confidentiality Requirements Engineering for Process Data
The application and development of process mining techniques face significant challenges due to the lack of publicly available real-life event logs. One reason for companies to abstain from sharing their data are privacy and confidentiality concerns. Privacy concerns refer to personal data as...
Inference Attacks for X-Vector Speaker Anonymization
We revisit the privacy-utility tradeoff of x-vector speaker anonymization. Existing approaches quantify privacy through training complex speaker verification or identification models that are later used as attacks. Instead, we propose a novel inference attack for de-anonymization. Our attack is...
Can Differentially Private Fine-Tuning LLMs Protect against Privacy Attacks?
Fine-tuning large language models LLMs has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and exposed. Although differential privacy DP offers strong...
Reveal-Or-Obscure: a Differentially Private Sampling Algorithm for Discrete Distributions
We introduce a differentially private DP algorithm called reveal-or-obscure ROO to generate a single representative sample from a dataset of $n$ observations drawn i.i.d. from an unknown discrete distribution $P$. Unlike methods that add explicit noise to the estimated empirical distribution, ROO...