Amirhossein Farzam

Mr. Amirhossein Farzam


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2020 in Theory in Biosciences
Verified
Journal Article
Open access
PDF file
MEMarzieh Eidi
Marzieh Eidi
AFAmirhossein Farzam
Amirhossein Farzam
WLWilmer Leal
Wilmer Leal
ASAreejit Samal
Areejit Samal
JJJuergen Jost
Juergen Jost
The relations, rather than the elements, constitute the structure of networks. We therefore develop a systematic approach to the analysis of networks, modelled as graphs or hypergraphs, that is based on structural properties of (hyper)edges, instead of vertices. For that purpose, we utilize so-called network curvatures. These curvatures quantify the local structural properties of (hyper)edges, that is, how, and how well, they are connected to others. In the case of directed networks, they assess the input they receive and the output they produce, and relations between them. With those tools, we can investigate biological networks. As examples, we apply our methods here to protein–protein interaction, transcriptional regulatory and metabolic networks.

6 January 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AFAmirhossein Farzam
Amirhossein Farzam
PMParham Moradi
Parham Moradi
SMSaeedeh Mohammadi
Saeedeh Mohammadi
ZPZahra Padar
Zahra Padar
ASAlexandra A. Siegel
Alexandra A. Siegel
For Iranians and the Iranian diaspora, the Farsi Twittersphere provides an important alternative to state media and an outlet for political discourse. But this understudied online space has become an opinion manipulation battleground, with diverse actors using inauthentic accounts to advance their goals and shape online narratives. Examining trending discussions crossing social cleavages in Iran, we explore how the dynamics of opinion manipulation differ across diverse issue areas. Our analysis suggests that opinion manipulation by inauthentic accounts is more prevalent in divisive political discussions than non-divisive or apolitical discussions. We show how Twitter’s network structures help to reinforce the content propagated by clusters of inauthentic accounts in divisive political discussions. Analyzing both the content and structure of online discussions in the Iranian Twittersphere, this work contributes to a growing body of literature exploring the dynamics of online opinion manipulation, while improving our understanding of how information is controlled in the digital age.

7 December 2020 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AFAmirhossein Farzam
Amirhossein Farzam
ASAreejit Samal
Areejit Samal
JJJuergen Jost
Juergen Jost
Despite the growing interest in characterizing the local geometry leading to the global topology of networks, our understanding of the local structure of complex networks, especially real-world networks, is still incomplete. Here, we analyze a simple, elegant yet underexplored measure, ‘degree difference’ (DD) between vertices of an edge, to understand the local network geometry. We describe the connection between DD and global assortativity of the network from both formal and conceptual perspective, and show that DD can reveal structural properties that are not obtained from other such measures in network science. Typically, edges with different DD play different structural roles and the DD distribution is an important network signature. Notably, DD is the basic unit of assortativity. We provide an explanation as to why DD can characterize structural heterogeneity in mixing patterns unlike global assortativity and local node assortativity. By analyzing synthetic and real networks, we show that DD distribution can be used to distinguish between different types of networks including those networks that cannot be easily distinguished using degree sequence and global assortativity. Moreover, we show DD to be an indicator for topological robustness of scale-free networks. Overall, DD is a local measure that is simple to define, easy to evaluate, and that reveals structural properties of networks not readily seen from other measures.

1 January 2024
Verified
Conference Paper
Open access
PDF file
AFAmirhossein Farzam
Amirhossein Farzam
SSShashank Shekhar
Shashank Shekhar
IMIsaac Mehlhaff
Isaac Mehlhaff
MMMarco Morucci
Marco Morucci
Amirhossein Farzam, Shashank Shekhar, Isaac Mehlhaff, Marco Morucci. Proceedings of the 11th Workshop on Argument Mining (ArgMining 2024). 2024.

20 November 2020 in arXiv
Verified
Preprint
Open access
PDF file
AFAmirhossein Farzam
Amirhossein Farzam
ASAreejit Samal
Areejit Samal
JJJuergen Jost
Juergen Jost
Despite the growing interest in characterizing the local geometry leading to the global topology of networks, our understanding of the local structure of complex networks, especially real-world networks, is still incomplete. Here, we analyze a simple, elegant yet underexplored measure, `degree difference' (DD) between vertices of an edge, to understand the local network geometry. We describe the connection between DD and global assortativity of the network from both formal and conceptual perspective, and show that DD can reveal structural properties that are not obtained from other such measures in network science. Typically, edges with different DD play different structural roles and the DD distribution is an important network signature. Notably, DD is the basic unit of assortativity. We provide an explanation as to why DD can characterize structural heterogeneity in mixing patterns unlike global assortativity and local node assortativity. By analyzing synthetic and real networks, we show that DD distribution can be used to distinguish between different types of networks including those networks that cannot be easily distinguished using degree sequence and global assortativity. Moreover, we show DD to be an indicator for topological robustness of scale-free networks. Overall, DD is a local measure that is simple to define, easy to evaluate, and that reveals structural properties of networks not readily seen from other measures.

23 February 2026 in arXiv
Verified
Preprint
Open access
PDF file
AFAmirhossein Farzam
Amirhossein Farzam
MBMajid Behabahani
Majid Behabahani
MMMani Malek
Mani Malek
YNYuriy Nevmyvaka
Yuriy Nevmyvaka
GSGuillermo Sapiro
Guillermo Sapiro
Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries to hide the malicious goal of their request by manipulating its framing to induce compliance. Because these attacks maintain malicious intent through a flexible presentation, defenses that rely on structural artifacts or goal-specific signatures can fail. Motivated by this, we introduce a self-supervised framework for disentangling semantic factor pairs in LLM activations at inference. We instantiate the framework for goal and framing and construct GoalFrameBench, a corpus of prompts with controlled goal and framing variations, which we use to train Representation Disentanglement on Activations (ReDAct) module to extract disentangled representations in a frozen LLM. We then propose FrameShield, an anomaly detector operating on the framing representations, which improves model-agnostic detection across multiple LLM families with minimal computational overhead. Theoretical guarantees for ReDAct and extensive empirical validations show that its disentanglement effectively powers FrameShield. Finally, we use disentanglement as an interpretability probe, revealing distinct profiles for goal and framing signals and positioning semantic disentanglement as a building block for both LLM safety and mechanistic interpretability.