Search Results for author:
Found 12 papers, 6 papers with code
Can LLMs Understand Computer Networks? Towards a Virtual System Administrator
Private LLMs achieve noteworthy results in small and medium networks, while challenges persist in comprehending complex network topologies, particularly for open-source models.
"All of Me": Mining Users' Attributes from their Public Spotify Playlists
In this work, we investigate the relationship between Spotify users' attributes and their public playlists.
Invisible Threats: Backdoor Attack in OCR Systems
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents.
Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability
An alarming side-effect of evasion attacks is their ability to transfer among different models: this property is called transferability.
Boosting Big Brother: Attacking Search Engines with Encodings
Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation.
Social Honeypot for Humans: Luring People through Self-managed Instagram Pages
However, by choosing an appropriate content topic, this attractive mechanism could be extended to any OSN users, rather than only luring malicious actors.
Going In Style: Audio Backdoors Through Stylistic Transformations
This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects.
SoK: Explainable Machine Learning for Computer Security Applications
The security literature sometimes also fails to disentangle the role of the various stakeholders, e. g., by providing explanations to model users and designers while also exposing them to adversaries.
The Cross-evaluation of Machine Learning-based Network Intrusion Detection Systems
By using XeNIDS on six well-known datasets, we demonstrate the concealed potential, but also the risks, of cross-evaluations of ML-NIDS.
Captcha Attack: Turning Captchas Against Humanity
Content moderators constantly monitor these online platforms to prevent the spreading of inappropriate content (e. g., hate speech, nudity images).
Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack
The increased demand for machine learning applications made companies offer Machine-Learning-as-a-Service (MLaaS).
All You Need is "Love": Evading Hate-speech Detection
With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem.
